Source Shelf: a short, owner-approved list of industry reports your team reads, and a way to read them
by PaperChaseWebb
Keep a small set of major industry reports as your team's default evidence base: each with its edition, publish date, link on the publisher's own site, the date someone last looked for a newer edition, and a note on what the publisher sells. Read any one of them against three questions (what is changing, who is struggling, what could help them), with word-for-word quotes and page numbers, the third answer marked as your inference, and every figure matched to its quote. Every add, drop and replace waits for the owner's yes. Fifteen read-only checks run on the folder.
- Price
- $19
- Difficulty
- Intermediate
- Setup
- 1 hr
- Format
- .md file
source-shelf-owner-approved-industry-reports-read-three-ways.md · 83 KB · instant download after checkout
Want this built for you instead? We can build it for you.
What you end up with
When someone on your team cites a report, you can open which edition it was, where the publisher put it, who paid for it, and the exact sentence and page behind every figure; and no report joins or leaves the shelf without the owner's yes.
What you get
- 19 sections in one .md file
- The shelf folder: shelf.json, reports, changes, readings, proposals and a ledger, with blank templates and a starter list of 16 candidate series (publishers only, no figures)
- A three-question reading: what is changing, who is struggling, what could help them, with quote and page rules and help kept as inference
- shelf.py: gate (exit 0, 11, 12), due, edition checks recorded in a ledger, a one-page shelf.md, owner approval tied to a sha256, verify, apply and one use per yes
- shelf_check.py: fifteen read-only checks, with a seeded test shelf (15 findings, then 0)
- A skill file for Claude Code, Codex and Hermes, an AGENTS.md snippet and a Grok Bot rules block
- Ten prompts, a failure table and a worked example
- A look at research templates, research agents, report publishers and report-list funnels, with sources
Who it is for
Anyone who keeps quoting the same few reports and wants those quotes current, traceable to a page, and read the same way every time.
Works with
Solid chips: the agent is named in this listing's own tools list. Dashed chip: A skill file for Claude Code, Codex and Hermes, an AGENTS.md snippet and a Grok Bot rules block; the scripts were tested on Linux with Python 3.13, the agent files were not loaded inside each harness and the method was not run on real reports.
Tools needed
Cost to run: The pack is the only purchase. The scripts use no model tokens; reading reports uses your agent's usual tokens. Some reports are paid or gated, and the owner decides whether to get them.
Time to result: A ratified shelf and a first reading in an afternoon
How it works
Run the tests
Copy the source-shelf folder and run sh test_all.sh.
Expected: 15 findings on the seeded shelf and 0 on the fixed one, 15 of 15 single faults caught alone, checker tests 60 passed, shelf.py tests 60 passed, exit 2 on a missing folder.
Pick and fill candidates
Run shelf.py init, fill shelf.json with the owner and lanes, then use prompts 1 and 2 to fill candidate rows from the publisher's own pages and write one add change per report.
Expected: Each candidate has an https link on the publisher's domain, an edition, a publish date and a note on what the publisher sells.
Get the yes
The owner ratifies the rules and approves each add at their own terminal. The agent runs shelf.py verify and apply.
Expected: Every shelved report has a ledger row tied to the owner's yes, and the checker shows 0 findings.
Read one report
Use prompts 4 to 7: changing and struggling with quotes and pages, help as your inference, then up to two proposals. Run the checker and shelf.py report.
Expected: A shelf.md the owner can read in five minutes, with every figure matched to its quote.
Sample prompts, free to use
Open the publisher's own page for <series>. Fill the reports.csv row as a candidate: edition and publish date exactly as the page shows them, the link on that domain, access, cadence, basis, interest, lane and why. Then write an add change. If the report is behind a form or payment, stop and tell me.
Prompt 2 of 10.
From the same read, write the struggling row. Name who, as a kind of person or business. Quote the report and give the page. If the report does not say anyone is struggling, write that and stop.
Prompt 5 of 10.
List every number in readings.csv. For each, show the quote it came from. If any number is not in its quote, take it out of the answer.
Prompt 8 of 10.
Free preview of the file
# Source Shelf: a short, owner-approved list of reports your team reads, and a way to read them Version 1.0, 2026-10-29. By PaperChaseWebb. A method and a working folder for keeping a small set of major industry reports as your team's default evidence base, each with its edition, publish date, link on the publisher's own site and a note on what the publisher sells, plus a way to read any one of them against three questions: what is changing, who is struggling, and what could help them. Seven plain files, a script that gates what an agent may do, records edition checks, applies the owner's shelf changes and writes a one-page shelf, a read-only checker with fifteen checks, templates, a starter list of candidate series, a seeded test set, ten prompts and the tests, all Python 3 standard library. Works with Claude Code, Codex and Hermes through a skill file and an AGENTS.md snippet, and with Grok Bot through a rules block. Tested as described in section 11: everything ran on Linux with Python 3.13, including owner approvals typed at a pseudo-terminal. The skill file, snippet and rules block were not loaded inside the harnesses for this release, and the method has not been run on real reports. Each is marked where it matters. Lists of "reports that will shape your next business idea" are easy to find and easy to save. Most of them link to a post about the report rather than the report, give no edition, and say nothing about who paid for the research. Some are handed out only to
Test record
- Date
- Oct 29, 2026
- What was run
- shelf_check.py on a seeded shelf and a fixed copy, each planted fault alone, a missing input, and the unit tests. Linux, Python 3.13.
- Result
- 15 findings on the seeded shelf, 0 on the fixed one; 15 of 15 planted faults caught alone; exit 2 on missing input; nothing written. 60 checker and 60 shelf.py tests passed, 0 failed.
- Not run
- Real reports; the fixture is made up. The agent files inside Claude Code, Codex, Hermes or Grok Bot. Windows.
Copied from this item's dated test notes. What was not run stays in.
Worth knowing
- The method has not been run on real reports; every publisher, report, quote and figure in the fixture and the worked example is made up. The starter list names publishers and series only, with no editions or figures, and was not checked for current editions.
- A report tells you what its authors found among the people they asked. The pack does not claim that a struggling group in a report will buy anything; pair it with the Problem Mining Loop or your own calls for that.
- The skill file, AGENTS.md snippet and Grok Bot rules block were not loaded inside Claude Code, Codex, Hermes or Grok Bot. Linux only; Windows was not tested. The scripts open no network connection; your agent reads pages with its own tools.
- The approval step refuses piped input and the environment variables Claude Code, Codex, Hermes and Grok Bot set. That stops an agent approving its own change; it is not a lock against someone with the same account.
- On 2026-10-29, on Linux with Python 3.13: shelf_check.py gave 15 findings on the seeded shelf (each check once) and 0 on the fixed one, caught 15 of 15 single faults with only its own check, wrote nothing, and exited 2 on a missing folder, missing reports.csv or broken shelf.json; checker tests 60 passed, 0 failed; shelf.py tests at a pseudo-terminal 60 passed, 0 failed.
Questions
Which reports should be on it?
Ones that come out on a schedule, say who they asked or what data they used, and cover one of your lanes better than anything else you have. The starter list gives sixteen series to consider, and you check the current edition on each publisher's page.
Does it give me the reports' findings?
No. It quotes no real report and gives no figures from one. It gives you a way to read them and keep what you read checkable.
What about reports behind a form or a paywall?
The agent stops and tells the owner. Agents never buy, register, subscribe, give an email address or comment to unlock a report.
How is this different from the Problem Mining Loop?
The shelf reads what researchers published; the loop reads what buyers say in their own words. A struggling group the shelf finds becomes a buyer type the loop goes and checks.
Details
Version 1.0 · Updated Oct 29, 2026 · Markdown version of this page
License: Use for your own business and for shelves you keep for clients. Do not resell or republish the pack itself. Download terms
Related
Source Shelf: five rules and a five-check script (free sample)
From the Source Shelf: five rules for a small list of industry reports (one owner, link to the publisher not the post, dated and checked, three questions every time, every figure with its quote), and a read-only script that checks one small file for them.
Problem Mining Loop: real complaints, graded and counted, before you build anything
Find out what one kind of buyer complains about, in their own words. Every complaint is a row with the link, the date posted, the exact quote and a salted key in place of the poster's handle, graded gripe, pain, budget or buyer. Clusters count independent posters, not posts, and leave out prompted answers and your own accounts. A cluster is proposed only when enough people at pain or higher, from more than one source, say so and one shows money. Public pages only, robots.txt and terms checked, GET only, and nobody in the community is ever contacted. Proposals wait for your yes at your own terminal; fifteen read-only checks run on the set.
Research Contract for Agents: claims, sources and dates your agent must keep
A contract your agent follows on every research run, kept as plain files: each claim with its source, date and confidence, primary sources before secondary, quotes word for word with a location, contradictions listed, unknown allowed, and no citation to anything it did not open. A fifteen-check script reads the folder and names every break in a plain sentence, and nothing is published or acted on until the owner approves the exact report by its sha256.
Evidence Standard: what counts as proof for each kind of agent work, who checks it, and what is refused
Agents report done from the plan as often as from the result. Five plain files write down, for each class of work, the proof that counts, who checks it (never the producer), what is refused and how long proof is kept. Agents log each claim with its evidence, seal it by sha256 and report in the words evidence.py say allows: done, partly done with the gap named, waiting on the owner, or reported, not verified. The agent's own summary is never proof. Fifteen read-only checks run on the standard and the claims ledger.
Check the Claim (expanded edition): a method, prompts and a skill for checking AI claims
Make your agent check income, tool, popularity, quote, news and offer claims before they reach a brief, a pitch, a purchase or a post: label how much was read, run the creator's own arithmetic, trace sources back to first hand, and give each claim one of five verdicts on a card the owner approves. v1.1 adds an evidence level label (full, caption, summary or wall), four new arithmetic tests, a section on tracing a source back to first hand, screens for offers, quotes and slogans, four more red flags, a sixth worked example, a claim folder with a fourteen-check read-only checker and an owner approval helper, agent files for Grok Bot, Claude Code, Codex and Hermes, and twelve new prompts (26 in all). Price unchanged.
Compile Your Research: a cited, checked second brain your agents keep
Your agent compiles saved sources into linked markdown pages where every fact cites its file, conflicts get their own page, and nothing is the record until a person ratifies it. Four folders, ten rules, seven page types, ten prompts, a health check script that needs no AI, and a seeded test vault with nine planted problems.
Agent Readiness Self-Check: score one workflow before you hand it to an AI agent
A free self-check for agencies and small businesses. Name the decision, then score one workflow across eight areas (workflow mapped, data access, approval gates, owner per agent, handoffs, cost tracking, security and vetting, measurement) with an evidence rule, three gate rules and a skeptical pass, and read your band and the next steps it allows. v1.1 starts with the decision the score will change, scores unknowns as unknown, adds rules for conflicting facts and lookalike public records, ties every band to the next steps it allows with the Production Readiness Audit before go-live, makes owner approval concrete (prepared and approved status, a one-reply approval line, decisions the agent must leave open, a done test), adds agent files for Grok Bot, Claude Code, Codex and Hermes, a second worked example (missed call to booked job), a readiness folder with a fifteen-check read-only checker, a front door test with four questions to ask anyone selling you an agent install, and a plain note on how it was tested. Still free.
Compounding Offer Audit: score an offer on six tests, find its weakest point, change one thing
Score each thing you sell from 0 to 3 on six tests: recurring, productized, systemized, owned demand, compounding, and whether growing it would make the owner's week better. Every score needs a checkable fact and its source, or the word unknown and the fact you are missing; no 3 on the owner's say-so, and no total. The audit names the weakest test, treats a low life score as a veto on growth, and proposes one change with a success test and a date. Every change waits for the owner's yes. Fifteen read-only checks run on the folder.
Startup Credits Sweep: an eligibility matrix, honest applications and an expiry ledger
Sweep startup programs for cloud, AI API and SaaS credits from your own facts. Each fact names its record; each program is read on its own page with the date; each requirement is marked meets, fails or unknown against one fact, and the matrix sets the verdict. Application drafts cite every fact and say it word for word, so nothing is stretched or invented to fit a form. A ledger counts credits only after the approval notice and reminds you before each grant expires. Every application waits for the owner's yes, and the owner submits it by hand. Fifteen read-only checks run on the folder.
AI Answer Visibility Check: does an assistant name you when a buyer asks, and who gets named instead
Ask each buyer question three times per assistant in fresh chats, paste the answers, and get a dated record of where you were named, where you were missed, who was named instead and which sources each answer cited. Fifteen read-only checks keep it honest: no brand in the question, three runs before a gap, answers hashed as given, nothing older than a month treated as current, and only your own brand. Page changes wait for the owner's yes.