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 skills/spair/task-pipeline/self-improvenpx skills add SpaiR/task-pipeline --skill self-improvegit 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/skills/spair/task-pipeline/self-improve)<a href="https://agentmods.dev/skills/spair/task-pipeline/self-improve"><img src="https://agentmods.dev/badge/skills/spair/task-pipeline/self-improve.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 | $0.00076 | $0.04016 |
| Opus 5 | $0.00038 | $0.02008 |
| Sonnet 5 | $0.00015 | $0.00803 |
| Haiku 4.5 | $0.00008 | $0.00402 |
Grade A, and why
self-improve 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 5d 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve this repository (the task-pipeline skills repo itself) — not by fixing rule violations (that is /self-audit), but by raising quality where nothing is broken yet. Four lenses run in parallel as named read-only subagents: Clarity, Leanness, Coverage, Ergonomics.
improve vs audit — the split that defines this skill
/self-audit asks "does the repo obey its own declared rules?" — it has an oracle (CLAUDE.md invariants, the artifact contract in docs/contract.md, the real skills/ tree), the fix direction is determined, and every gated finding is applied.
/self-improve asks "nothing is violated — but where is the repo weaker than it could be?" — there is no oracle. An "improvement" is a judgement call, and its direction is a design decision, not a mechanical correction. That is the literal difference between fixes (audit) and improvements (improve), and it drives the whole apply model:
- Audit applies everything that passes its gate — the source of truth says which way to go.
- Improve applies only a narrow, mechanical, behavior-preserving subset automatically, at a higher confidence bar, and proposes everything that changes the design for the user to greenlight. Improvements that reshape a flow, merge sections, or add a guardrail are decisions a human must nod at.
Boundary rule (hard): if a lens finds an actual violation of a declared rule (an invariant, a producer↔consumer mismatch, README↔code drift), that is audit's job, not improve's. The agent must set defer: self-audit on it and not propose a fix. /self-improve never edits under the banner of a rule violation — it only makes not-yet-broken things better.
This is a meta-skill. It operates on the repo's own files (skills/*/SKILL.md, skills/_lib/*.sh, skills/validate/validate.sh, CLAUDE.md, README.md, docs/contract.md), not on .task/* artifacts. The pipeline it improves is the chat-first capture protocol (six user skills — grill, to-task, to-plan, to-roadmap, to-spec, roadmap-to-workflow — plus the bash-only validate); the repo-level agents/ directory holds exactly one file, agents/code-reviewer.md. It can be invoked at any time.
Input:
- Optional scope hint: $ARGUMENTS (e.g. a single skill name to focus on; default: full repo).
- Optional flag
--propose-only(alias--dry-run) in $ARGUMENTS: apply nothing; report both tiers only. (This is a flag of the meta-skill itself, not of the audited pipeline — the pipeline is flag-free.)
Precondition (hard-stop): This skill is local to the task-pipeline repo. Verify the working directory contains skills/to-task/, skills/validate/, and CLAUDE.md at the repo root. If not, stop with: "This skill is local and only works inside the task-pipeline repository."
Communication language: Russian (per global user instructions). Findings text stays in English (it grounds in English source files and matches the existing auditor convention).
Why a separate set of agents from self-audit? Audit's three lenses are conformance checks (Invariants, Contract, Docs-sync) — reality-vs-declared-rule. Improve's four lenses are quality checks with no oracle. Different question, different failure modes, different apply posture — hence a separate agent set.
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.
- 5d ago First seen · 202 lines · 76 tokens per session scan A 33fe1ba0845f
self-improve is a skill published in the GitHub repository SpaiR/task-pipeline (7 stars, last pushed 3d ago), licensed MIT. It adds 76 tokens to every session and 4,016 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 skills, from other repositories
errata
Correct what was written wrong — the binding line rewritten in place, the record it came from appended to and never touched, both carrying the evidence that overturned it. Use when a run, a file, or the user contradicts something already written in a work file, a plan's contract, the glossary, or the decision index…
setup-working-genius
Per-repo configuration — pin the work-file directory, verify commands, and issue tracking, seed the project docs, and leave the pointer that tells every future session this project works this way.
decision-record
Keep the index of the project's settled decisions in .genius/DECIDED.md — one line per decision, pointing at the fight that settled it, earned by one test: would a future stranger re-fight this? Use when such a decision lands, when a design might contradict a settled one, or when another skill needs the index…
domain-glossary
Maintain the project's shared vocabulary in CONTEXT.md — challenge conflicting terms, sharpen fuzzy language, record resolutions inline. Use when a term conflicts with or is missing from the glossary, when a decision names a new concept, or when another skill needs the glossary discipline.
dw-grain
Audit code just written for excess the gate cannot see: a helper reinvented beside its canonical home, a wrapper with one caller, config for a case that never occurs, a shape the neighbouring files build differently, code this change stranded. One table, and every row is a deletion or a reuse. Explicit-invoke only.
dw-doctor
Read-only environment diagnostic for a solo-lane repo: whether the tools the hooks and skills assume are installed and whether the repo's guardrails will really fire, each gap reported with a copy-paste fix.