Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/roomi-fields/paper-trailWrote 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/roomi-fields/paper-trail/paper-trail-registry-cleanup)<a href="https://agentmods.dev/commands/roomi-fields/paper-trail/paper-trail-registry-cleanup"><img src="https://agentmods.dev/badge/commands/roomi-fields/paper-trail/paper-trail-registry-cleanup/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/roomi-fields/paper-trail/paper-trail-registry-cleanup"><img src="https://agentmods.dev/badge/commands/roomi-fields/paper-trail/paper-trail-registry-cleanup.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 | $0.00109 | $0.00742 |
| Opus 5 | $0.00055 | $0.00371 |
| Sonnet 5 | $0.00022 | $0.00148 |
| Haiku 4.5 | $0.00011 | $0.00074 |
Grade A, and why
paper-trail-registry-cleanup 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 11d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/paper-trail:registry-cleanup — Nettoyage historique du registre
Distinct de resolve-textbooks (qui est session-locale, ne traite que les
refs textbook ingérées sans year/title) : registry-cleanup est global,
scanne tout le registre et inclut aussi les duplicates avec suffixes
numériques moches.
Usage
/paper-trail:registry-cleanup # dry-run (montre les décisions)
/paper-trail:registry-cleanup --apply # applique
Ce que fait Claude
-
Liste les candidates :
python3 -m pipeline registry-cleanup --list > /tmp/registry_cleanup_candidates.jsonInclut :
- Refs
*_0000_*ou_untitled(placeholders INGEST) - Refs avec year vide/
0000/nd/None - Refs avec title vide
- Refs avec suffixe numérique (
_2,_2_3,_2_3_4, etc.) — artefacts des runs précédents
- Refs
-
Invoque le sub-agent
textbook-resolveravec le JSON :Agent(subagent_type="paper-trail:textbook-resolver", prompt=<contenu /tmp/registry_cleanup_candidates.json>)Le sub-agent applique ses règles :
merge_intosi sibling complet,completesi textbook canonique reconnu,blockedsinon. -
Sauve le JSON de décisions dans
/tmp/registry_cleanup_decisions.json. -
Mode dry-run (défaut) : affiche les décisions par catégorie, demande confirmation avant
--apply. -
Mode
--apply:python3 -m pipeline registry-cleanup \ --apply-from /tmp/registry_cleanup_decisions.jsonLes
merge_intodéclenchent automatiquementsota_sync(les wikilinks dans tous les SOTAs concernés sont mis à jour). -
Récap final : N merged + sync, N completed, N blocked.
Quand l'utiliser
- Après migration vers v0.2.0+ : rattrape les vieux duplicates
- Tous les 3-6 mois : hygiène registre (au fur et à mesure que le registre accumule des duplicates)
Garde-fous
- Sub-agent ne fabrique JAMAIS year/title incertain (confidence < 80% → blocked).
- Fusions traçables : la ref source passe en
retractedavecretracted_reason: merged_into:<target>. Réversible via git. - Le hook
sota_syncautomatique met à jour TOUS les SOTAs qui citent les slugs mergés. - Backup git du vault avant chaque mutation (
_ensure_git_backup).
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.
- 11d ago First seen · 71 lines · 109 tokens per session scan A 13f9ccc64552
paper-trail-registry-cleanup is a command published in the GitHub repository roomi-fields/paper-trail (5 stars, last pushed 7d ago), licensed MIT. It adds 109 tokens to every session and 742 once invoked, about $0.0005 per session on Opus 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 2026-08-31.
Other commands, from other repositories
gh-security-review
Use to perform a dedicated security review of current branch changes before pushing.
gh-release
Create a new release for the marketplace or a specific plugin.
ledger-research
Launch parallel evidence collection across all active research pillars.
ledger-spec
Generate constrained PRD and architecture documents where every section cites decisions.
quick-research
Quick research with source verification (lighter than /deep-research).
gh-status
Quick overview of current GitHub workflow state.