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/mauhpr/agentlint-pluginWrote 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/mauhpr/agentlint-plugin/lint-config)<a href="https://agentmods.dev/commands/mauhpr/agentlint-plugin/lint-config"><img src="https://agentmods.dev/badge/commands/mauhpr/agentlint-plugin/lint-config/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/mauhpr/agentlint-plugin/lint-config"><img src="https://agentmods.dev/badge/commands/mauhpr/agentlint-plugin/lint-config.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 | $0.00009 | $0.00245 |
| Opus 5.5 | $0.00004 | $0.00098 |
| Sonnet 5.5 | $0.00002 | $0.00049 |
| Haiku 4.5 | $0.00001 | $0.00024 |
Grade A, and why
lint-config 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 15d 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
Read the agentlint.yml file in the project root and display:
- Current severity mode (standard/strict/relaxed)
- Active packs (built-in and custom)
- Rule overrides
- Custom rules directory and custom packs
- CLI integration commands (if configured)
If the user wants to change settings, edit the agentlint.yml file.
Notes:
universalandqualityare always active, even with an explicitpacks:list;exclude_packs: [quality]turns one off deliberately.- The
securityandautopilotpacks are opt-in. - Custom packs activate when listed in
packs:andcustom_rules_diris set. - CLI integration runs external tools (linters, scanners) on PostToolUse.
- Use
agentlint list-rulesto see all rules, oragentlint list-rules --pack <name>to filter. - Run
agentlint doctorto diagnose misconfigurations. - Full reference: https://github.com/mauhpr/agentlint/blob/main/docs/configuration.md
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.
- 15d ago Changed · +1 lines febedfe6e215
- 1mo ago First seen · 22 lines · 9 tokens per session scan A d5bfad7c5689
lint-config is a command published in the GitHub repository mauhpr/agentlint-plugin (3 stars, last pushed 4d ago), licensed MIT. It adds 9 tokens to every session and 245 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
update
Update Slime to the latest version.
fable-eval
Run the fable-mode eval suite (probes → pairwise judge → report). Costs tokens — runs headless claude many times. Optional arg: a probe id substring to filter.
decree
Issue a decree. Seats the organization on first use, then dispatches the teams.
report
The full account of the current decree — every figure verified before stated.
review
Verification review of a named agent's claim. Ends in acquittal or replacement.
help
Explain what goalkeeper is and how to use it.