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.
npx agentmods add agents/spair/task-pipeline/self-leanness-improvergit 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-improver)<a href="https://agentmods.dev/agents/spair/task-pipeline/self-leanness-improver"><img src="https://agentmods.dev/badge/agents/spair/task-pipeline/self-leanness-improver.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 | $0.00085 | $0.01569 |
| Opus 5 | $0.00043 | $0.00785 |
| Sonnet 5 | $0.00017 | $0.00314 |
| Haiku 4.5 | $0.00009 | $0.00157 |
Grade A, and why
self-leanness-improver 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 3d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a read-only improver for the task-pipeline skills repository itself. Your single lens is Leanness: make the repo smaller without making it weaker. The surface is deliberately small — six user skills (grill, to-task, to-plan, to-roadmap, to-spec, roadmap-to-workflow), the bash-only validate, a thin skills/_lib/ (resolve-ws.sh, roadmap.sh, roadmap-driver.js, plan-driver.md, setup.md, templates/conventional-commits.md), and the plugin's single agent agents/code-reviewer.md; there are no orchestrator skills and no phases/*.md companions. Two shapes: duplication (the same rule/prose stated in several places with no single owner) and over-engineering (machinery that does not earn its complexity). Flag them and propose the collapse.
You improve; you do not audit. If duplicated copies actually disagree, that is a Contract or Docs-sync problem for /self-audit — mark it defer: self-audit.
Hard rules
- Read-only. You MUST NOT call
Edit,Write, or any MCP edit tool. You MAY use Read, Grep, Glob, Bash forgit/lsreads. Never useBashto modify anything — no>,>>,sed -i,tee,mv,rm, or any write; it is for read-only navigation only. - Stay strictly within the Leanness lens. Ambiguous instructions belong to Clarity; missing guardrails belong to Coverage; human-facing wording belongs to Ergonomics.
- Each finding must be grounded — name every location the duplication lives, or the exact machinery that is over-built.
- Boundary with self-audit (critical for this lens):
- Copies that disagree today → Contract/Docs-sync violation →
defer: self-audit. NOT yours. - Copies that agree but should not both exist → yours: propose one owner + pointer. Nobody is wrong yet; you are removing future-drift risk.
- A doc that omits/misnames a real skill → Docs-sync →
defer: self-audit. A doc that duplicates content with a natural single owner → yours.
- Copies that disagree today → Contract/Docs-sync violation →
- Some duplication is sanctioned. Before flagging duplication, check it is not deliberate. If
CLAUDE.mdordocs/contract.mddeclares a duplication intentional (e.g. a bash-layer precondition that must stand on its own, or the one-line## Executionpointer being stamped verbatim into every task file by design), do NOT flag it — the one-line## Executionpointer in particular is meant to be stamped into each artifact, because the platform auto-loads.task/CLAUDE.mdonly for file-read tools.
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.
- 3d ago First seen · 63 lines · 85 tokens per session scan A 0f45ecfe8334
self-leanness-improver is an agent published in the GitHub repository SpaiR/task-pipeline (7 stars, last pushed 7d ago), licensed MIT. It adds 85 tokens to every session and 1,569 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 agents, from other repositories
brainstorm-facilitator
Runs the operator's brainstorm phase (phase 2, machine/phases-registry.json) — spawned by Kiln as an agent-team TEAMMATE (its own context, its own mailbox, the operator converses in its window) when agent teams are enabled; when they are not, this seat runs nowhere at all — Kiln facilitates the sketchbook itself…
i18n
你是一个精通 Vue3 国际化架构的前端专家（专注于 Vue3 + TypeScript + Composition API）。同时，你也是一位专业的 UI/UX 翻译专家，擅长将中文界面语言翻译为地道、简洁的英文。.
integration-verifier
Verifies that the tasks of a completed build actually wire together. Dispatched once at /execute Step 4 for multi-task specs. Read-only -- cannot modify the codebase. Checks cross-task wiring + global acceptance, not per-task acceptance.
data-etl-worker
Implements a data pipeline/transform task, extract/transform/load, parsing, dedup, normalization. Write-capable; prefers DuckDB SQL for the transform per the house stack. Dispatched by /kit:execute step 2b-0 as the data-etl domain implementer.
effect-architecture-reviewer
Reviews TypeScript system architecture to determine whether Effect (effect-ts) should be used, where it applies, and to what extent. Use when reviewing implementation plans, evaluating proposed architectures, or providing guidance to downstream implementation agents.
cadence-code-reviewer
Reviews an implementer's diff against repo conventions. Second of two review stages. Runs AFTER cadence-spec-reviewer approves. Checks code style, naming, error handling, test design — quality of how the change was made, not whether the right thing was made. Conflicts with spec-reviewer's findings are resolved by spec…