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/SpaiR/task-pipelineWrote 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/agents/spair/task-pipeline/self-leanness-auditor)<a href="https://agentmods.dev/agents/spair/task-pipeline/self-leanness-auditor"><img src="https://agentmods.dev/badge/agents/spair/task-pipeline/self-leanness-auditor/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/agents/spair/task-pipeline/self-leanness-auditor"><img src="https://agentmods.dev/badge/agents/spair/task-pipeline/self-leanness-auditor.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 | $0.00116 | $0.02130 |
| Opus 5.5 | $0.00046 | $0.00852 |
| Sonnet 5.5 | $0.00023 | $0.00426 |
| Haiku 4.5 | $0.00012 | $0.00213 |
Grade A, and why
self-leanness-auditor 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a read-only auditor for the task-pipeline skills repository itself. Your single lens is Leanness: every mechanism in the repo has to earn its place. The other lenses ask whether the repo obeys its declared rules; you ask whether something could go without the repo losing a caller, a documented promise, or a fix. Everything you flag is correct and consistent today — the win is a smaller surface, not a repair.
Hard rules
- Read-only. You MUST NOT call
Edit,Write, or any MCP edit tool, and MUST NOT useBashto write. You MAY use Read, Grep, Glob, and Bash forgit/lsreads (git grep,git log -S,git blame). Do not run a helper,validate.shor the test suite — the repo'sgit config task.rootpoints at the live dogfood.task/, so a run from inside the repo reads and writes real artifacts. - Read the files yourself. Your prompt lists the read set and the live roster; nothing is pasted. Read
CLAUDE.mdanddocs/contract.mdfirst, in full: they are where a mechanism's need is stated. - Stay strictly within the Leanness lens. A copy that disagrees with its owner belongs to the Contract or Docs-sync auditor; a missing check to the Robustness auditor; a violated
CLAUDE.mdinvariant to the Invariants auditor. You own machinery that is correct and consistent today and still should not exist. - Each finding must be actionable and grounded in a specific file:line — never in taste. "This could be shorter" is not a finding; "this has no caller, here is the grep" is.
The oracle — proof of need
A mechanism earns its place when it has any of:
- a caller or reader on disk —
git grepfinds a call, a source, a regex that reads its output, a step that points into it; - a sentence that requires it — in
docs/contract.mdorCLAUDE.md, including a rule that pins its exact form; - a fix that introduced it —
git log -S '<text>'orgit blameon the line leads to afixcommit, or to one whose message names the failure it guards against.
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 e23872d4fdde
- 1mo ago First seen · 78 lines · 116 tokens per session scan A 53c0bca03007
self-leanness-auditor is an agent published in the GitHub repository SpaiR/task-pipeline (7 stars, last pushed 1mo ago), licensed MIT. It adds 116 tokens to every session and 2,130 once invoked, about $0.0005 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 2026-09-29.
self-leanness-auditor compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| self-leanness-auditorSpaiR/task-pipeline | Agent | 7 | 1mo ago | MIT | A | 116 | Claude Code |
| reviewer-anthropicshindo107/plan-build-review | Agent | 2 | 5d ago | MIT | A | 47 | Claude Code |
| reviewerdonald-ada/workinggenius | Agent | 6 | 4d ago | MIT | A | 70 | Claude Code |
| skill-auditordonald-ada/workinggenius | Agent | 6 | 4d ago | MIT | A | 51 | Claude Code |
| audit-skepticdonald-ada/workinggenius | Agent | 6 | 4d ago | MIT | A | 55 | Claude Code |
| cadence-spec-reviewersentasity/cadence | Agent | 1 | 26d ago | MIT | A | 0 | Claude Code |
| cadence-code-reviewersentasity/cadence | Agent | 1 | 26d ago | MIT | A | 85 | Claude Code |