Borrowing it
Nothing to install: this file belongs to paullukic/coograph. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/paullukic/coograph/main/.github/skills/coograph-docs-restructure/SKILL.mdgit clone --depth 1 https://github.com/paullukic/coographWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/paullukic/coograph/coograph-docs-restructure)<a href="https://agentmods.dev/skills/paullukic/coograph/coograph-docs-restructure"><img src="https://agentmods.dev/badge/skills/paullukic/coograph/coograph-docs-restructure/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/paullukic/coograph/coograph-docs-restructure"><img src="https://agentmods.dev/badge/skills/paullukic/coograph/coograph-docs-restructure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00089 | $0.02869 |
| Opus 5.5 | $0.00036 | $0.01148 |
| Sonnet 5.5 | $0.00018 | $0.00574 |
| Haiku 4.5 | $0.00009 | $0.00287 |
Grade A, and why
coograph-docs-restructure scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Restructure the project's instruction files into the three tiers in
.github/layout/README.md: always-loaded root files (9K combined), workspace
routers (about 2K each), and on-demand feature docs (8K each), plus GOTCHAS.md.
Two phases with a hard stop between them: Propose writes an OpenSpec and
stops; Apply runs only after the user approves it.
Read .github/layout/README.md once before starting. It defines the tiers, the
config, the feature-doc frontmatter and the gotcha format.
The rule that matters most: no current-state fact is lost, and no stale fact survives. Old map sections are often out of date. Every fact is checked against the code and gets one of three marks:
[x] file:line: the code confirms it. Keep it.[kept: not in code]: the code can neither confirm nor contradict it (a deploy step, a console setting, a renewal date, team process). Keep it: in the area doc, or inGOTCHAS.mdwhen it is a trap. "Not provable from code" is never a reason to drop.[dropped: <reason>]: only when the code contradicts it, it is history rather than current state, or it duplicates another area.
Step 0: Resume or start
Look for a non-archived openspec/changes/*-docs-restructure/.
Approval is recorded on disk, not only in the conversation: the line
approved: <YYYY-MM-DD> in the change's .openspec.yaml (Phase 1 writes it
when the user approves, before the first Phase 2 edit).
- Found, no
proposal.mdyet: an aborted Phase 1. Reuse that directory and its date, and continue at Step 2. Keepnotes/layout-before.jsonwhen it parses as JSON with atierskey; otherwise retake it (Step 1). Never create a second directory with a new date. - Found,
proposal.mdbut noapproved:line: show it and ask whether to continue with it or discard it. Never start a second one alongside it. - Found and approved: this is a resume. Go to Phase 2 and continue at the first unticked task in its
tasks.md. Do not re-run Phase 1. Never regeneratenotes/areas/*.md,notes/gotchas.md,notes/rules.mdornotes/layout-before.json: they hold the only record of the original facts and the before numbers. Phase 2 only adds marks to them ([x],[kept: ...],[dropped: ...]) and writesnotes/layout-after.json. - An area name was given (
/coograph-docs-restructure auth): it applies only to an approved restructure. Run just that area's task. If no approved restructure exists, say so and stop. - Not found: Phase 1.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 227 lines · 89 tokens per session scan A e1845416ea71
coograph-docs-restructure is a skill published in the GitHub repository paullukic/coograph (17 stars, last pushed 12d ago), licensed MIT. It adds 89 tokens to every session and 2,869 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-07.
coograph-docs-restructure compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| coograph-docs-restructurepaullukic/coograph | Skill | 17 | 12d ago | MIT | A | 89 | Claude Code |
| managing-mcp-serversJetBrains/thinkrail | Skill | 7.8k | yesterday | Apache-2.0 | A | 62 | Claude Code, Codex |
| todosJetBrains/thinkrail | Skill | 7.8k | yesterday | Apache-2.0 | A | 58 | Claude Code, Codex |
| writing-workflow-skillsJetBrains/thinkrail | Skill | 7.8k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| ai-ml-developmenttravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 43 | Claude Code, Codex |
| performance-engineeringtravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 38 | Claude Code, Codex |
| case-interview-practicetravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 39 | Claude Code, Codex |