Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add trapoom555/claude-paperloom/plugin install claude-paperloomWrote 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/trapoom555/claude-paperloom/lint)<a href="https://agentmods.dev/commands/trapoom555/claude-paperloom/lint"><img src="https://agentmods.dev/badge/commands/trapoom555/claude-paperloom/lint.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.00585 |
| Opus 5 | $0.00016 | $0.00293 |
| Sonnet 5 | $0.00006 | $0.00117 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
lint 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 6d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/paperloom:lint
Read-only health check of the vault. All six checks run in scripts/lint.py.
Step 0 — greet the user
Before doing anything else, print this message exactly:
🔍 Running a vault health check — just a moment while everything gets tidied up ✨
Then proceed.
Steps
-
Resolve the vault path from
${CLAUDE_PLUGIN_CONFIG:vault_path}(default~/PaperLoom) — pass it raw to the script, which expands it. -
Run:
"${CLAUDE_PLUGIN_ROOT}/.venv/bin/python3" "${CLAUDE_PLUGIN_ROOT}/scripts/lint.py" "<vault-path>"The script performs:
- Frontmatter schema drift (required keys, enum values)
- Orphan pages (no inbound and no outbound wikilinks)
- Duplicate findings — new-vs-all only. A pair is flagged only if at least one member is "new" (default:
extracted-date ≥ today; override with--new-slugsor--since). Old-vs-old pairs are ignored. - Asymmetric contradicts / similar-to
- Stale wikilinks (target file missing)
- Date sanity (ISO format,
ingested-date ≥ publication-date)
For any dup pair found, the script by default creates a bidirectional
similar-toedge between the two findings (dedupe via linking, not by forcing the user to merge). Pass--no-link-similarto keep the run strictly read-only.Then appends a
lintline to<vault>/log.md. -
When called from
/paperloom:ingest, pass--new-slugs <slug1,slug2,...>so the dedup check focuses exactly on the freshly-written findings (don't rely on the date fallback — an earlier session could bump the "today" window). -
Relay the script's stdout to the user verbatim. Non-zero exit means issues exist — that is expected output, not a failure. Don't retry.
After the report
Offer — but do not auto-run — suggested fixes for the remaining issue categories (dup linking is already applied). The user drives remediation for schema drift, orphans, asymmetric edges, etc.
Guardrails
- The only write lint performs is creating
similar-toedges between duplicates. Schema / orphan / stale-link fixes are left to the user. - Pass
--no-link-similarif you want a strict read-only run. - Use
--jsonfor machine-readable output.
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.
- 6d ago First seen · 52 lines · 32 tokens per session scan A 8a28ba258a74
lint is a command published in the GitHub repository trapoom555/claude-paperloom (95 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 585 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
check-claude-plugin-sync
Diagnose drift between Claude Code plugin artifacts (skills, commands) and their OpenCode copies.
develop-fix
Systematic bug fixing with root cause analysis and regression prevention.
audit
Audit a DomainTome graph and report health (orphans, dangling edges, id hygiene, cycles). With no args, audits the active project. With a path, audits another project's graph without switching directory.
reconcile
Detect drift between code and DomainTome — dead sourcerefs, stale nodes, never-verified nodes. Read-only.
impact
Blast-radius analysis — what nodes are affected if this one changes?
doctor
Health check for greatcto. Shows pipeline state, missing artefacts, hook status, last run per agent, and permission-denied tail.