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-purge)<a href="https://agentmods.dev/commands/roomi-fields/paper-trail/paper-trail-purge"><img src="https://agentmods.dev/badge/commands/roomi-fields/paper-trail/paper-trail-purge/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-purge"><img src="https://agentmods.dev/badge/commands/roomi-fields/paper-trail/paper-trail-purge.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 | $0.00084 | $0.00608 |
| Opus 5 | $0.00042 | $0.00304 |
| Sonnet 5 | $0.00017 | $0.00122 |
| Haiku 4.5 | $0.00008 | $0.00061 |
Grade A, and why
paper-trail-purge 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 10d 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.
What it actually says
/paper-trail:purge <SOTA-path> — Nettoyage des wikilinks invalides
Étape 2 du pipeline cible refondu. Scanne tous les wikilinks d'un SOTA
et corrige les 6 cas invalides connus. Ne touche pas au registre
(c'est /paper-trail:arbitrate ou :registry-cleanup qui font ça).
Usage
/paper-trail:purge <SOTA-path> # dry-run (montre le plan)
/paper-trail:purge <SOTA-path> --apply # applique + backup git
Ce que fait Claude
-
Vérifie git initialisé dans le vault (sinon refuse).
-
Lance le plan :
python3 -m pipeline purge <SOTA-path>Affiche le récap : combien de wikilinks invalides par catégorie, avec les 15 premiers détails (numéro de ligne, wikilink, action prévue).
-
Si
--apply:python3 -m pipeline purge <SOTA-path> --applyCommit git auto avant modification, applique les substitutions et suppressions, affiche le compte final.
Les 6 cas détectés
| Cas | Détection | Action |
|---|---|---|
| A | wikilink vers ref state=retracted avec retracted_reason=merged_into:X |
remplace par [[X]] |
| A' | wikilink vers ref state=retracted pure |
strip (garde texte humain) |
| B | wikilink vers lastname_0000_* avec sibling lastname_YYYY_* validé |
remplace par sibling |
| C | wikilink avec suffixe numérique moche (_2_3, _2_3_4) |
strip |
| D | wikilink vers fichier technique (path 20_ATLAS/, 30_DEV/, ext .canvas) |
strip |
| D' | wikilink vers slug non-bibliographique TitleCase (IR_Spec_Preliminaire) |
strip |
Style
- Concis. Une phrase par étape.
- En cas d'erreur (SOTA introuvable, backup git échoué), explique et propose un retry.
- Pas de modification du registre (pas d'effet de bord).
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.
- 10d ago First seen · 53 lines · 84 tokens per session scan A fdf12a3207d4
paper-trail-purge is a command published in the GitHub repository roomi-fields/paper-trail (5 stars, last pushed 7d ago), licensed MIT. It adds 84 tokens to every session and 608 once invoked, about $0.0004 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.