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/.claude/commands/coograph-retro.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/commands/paullukic/coograph/coograph-retro)<a href="https://agentmods.dev/commands/paullukic/coograph/coograph-retro"><img src="https://agentmods.dev/badge/commands/paullukic/coograph/coograph-retro/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/commands/paullukic/coograph/coograph-retro"><img src="https://agentmods.dev/badge/commands/paullukic/coograph/coograph-retro.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 | $0.00000 | $0.00558 |
| Opus 5.5 | $0.00000 | $0.00223 |
| Sonnet 5.5 | $0.00000 | $0.00112 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
coograph-retro 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run a retro on this project's guardrails: measure which rules got broken across past sessions, what each session cost, and propose evidence-backed edits to instructions, hooks, and skills as an OpenSpec. Propose only; never apply.
The full procedure lives in .github/skills/coograph-retro/SKILL.md. Follow those steps exactly, with these Claude Code specific substitutions:
| SKILL.md tool | Claude Code equivalent |
|---|---|
vscode_askQuestions |
Ask the user directly in the conversation |
read_file |
Use Read tool |
run_in_terminal |
Use Bash tool |
Steps (summary)
- Status
python3 .github/retro/retro.py --status. Exit 4 means bootstrap (seed the registry, offer a transcript backfill from~/.claude/projects/<slug>/, with the user's consent). Exit 2 means the hooks are not installed; stop. - Analyze
python3 .github/retro/retro.py --report, then read.coograph/retro/report.mdandreport.json. Those are the only numbers you may cite. - Decide changes by type (new-hook, edit-rule, add-rule, new-instruction-file, prune-rule, structural, add-gotcha, prune-gotcha, escalate-gotcha) using the rules in the skill: evidence first, escalate instead of shouting, outcomes gate the block rung, budget pairing, no silent loosening.
- Write
openspec/changes/<date>-retro-<n>/with.openspec.yaml,proposal.md,specs/guardrails/spec.md,tasks.md(ending with Update registry and Rollback), andpatches/. - Report the summary table and stop.
Guardrails
- Never write outside the change directory.
- Never run
/coograph-applyyourself. - Never cite a number that is not in
report.json. - Never propose louder prose for an existing rule.
$ARGUMENTS
Models
Read the models block in openspec/config.yaml before delegating. When mode is
preset or per-task, pass that agent's model on the Agent call; when it is off
or unset, pass nothing and let the agent inherit the session model.
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 Changed 5b0576ee90d9
- 1mo ago Changed 677ffd345638
- 1mo ago Changed · +15 lines 078be2c4284d
- 1mo ago First seen · 27 lines · 0 tokens per session scan A 0783a244f25f
coograph-retro is a command published in the GitHub repository paullukic/coograph (17 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 558 tokens. 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 2026-09-20.
coograph-retro compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| coograph-retropaullukic/coograph | Command | 17 | 12d ago | MIT | A | 0 | Claude Code |
| pull-repostravisjneuman/.claude | Command | 107 | yesterday | MIT | A | 13 | Claude Code |
| security-scantravisjneuman/.claude | Command | 107 | yesterday | MIT | A | 6 | Claude Code |
| test-suitetravisjneuman/.claude | Command | 107 | yesterday | MIT | A | 7 | Claude Code |
| standardize-claude-mdtravisjneuman/.claude | Command | 107 | yesterday | MIT | A | 18 | Claude Code |
| helptravisjneuman/.claude | Command | 107 | yesterday | MIT | A | 9 | Claude Code |
| api-genhalflength-ampleness75/claude-code-recipes | Command | 2 | 23d ago | MIT | A | 14 | Claude Code |