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 skills add 45ck/skill-harness --skill self-improving-agent-loopgit clone --depth 1 https://github.com/45ck/skill-harnessWrote 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/45ck/skill-harness/self-improving-agent-loop)<a href="https://agentmods.dev/skills/45ck/skill-harness/self-improving-agent-loop"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/self-improving-agent-loop/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/skills/45ck/skill-harness/self-improving-agent-loop"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/self-improving-agent-loop.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 | $0.00039 | $0.00338 |
| Opus 5.5 | $0.00016 | $0.00135 |
| Sonnet 5.5 | $0.00008 | $0.00068 |
| Haiku 4.5 | $0.00004 | $0.00034 |
Grade A, and why
self-improving-agent-loop 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.
What it actually says
Self-Improving Agent Loop
Use this skill when a project wants agents to improve a workflow, skill, prompt, loadout, checker, or operating policy over time.
Loop
- Sense: collect issues, diffs, tests, traces, artifacts, user feedback, and handoff notes.
- Model: identify the task type, capability assumption, failure mode, and quality bar.
- Plan: choose one reversible improvement with explicit evidence.
- Act: change the smallest useful surface using existing project patterns.
- Gate: run tests, artifact checks, permission checks, and review gates.
- Learn: record a follow-up issue, durable memory, skill update, or checker proposal only when evidence supports it.
Governance
- Treat frontier models as capable of planning, synthesis, review, and context work when the digital surfaces are available.
- Keep deterministic scaffolding for repeatable validation, policy checks, manifests, and install wiring.
- Treat generated traces and self-assessments as evidence candidates, not proof.
- Require human approval for permission expansion, destructive actions, production data, publishing, merge, deployment, and policy changes.
- Keep domain-specific loops out of the core pack unless the pattern generalizes across projects.
Output
Loop Goal
Sensors
Failure Model
Reversible Action
Gates
Human Approval Boundaries
Learning Output
Next Issue Or Memory
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 First seen · 37 lines · 39 tokens per session scan A c5c2dc57c46f
self-improving-agent-loop is a skill published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 338 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
harness-init-runner
Initialize a lightweight repo-local Node.js harness (harness/ + .harness/) WITHOUT AIOS dependency. Use ONLY when you need a standalone, portable harness. If AIOS is installed, use aios-long-running-harness instead — it has rex Command hosting, ContextDB integration, and checkpoint recovery.
do-it-audit
Use when the user explicitly requests a deep repository or scoped audit; not for ordinary diff review.
do-it-skill-authoring
Use when creating or revising a do-it skill, its description, references, or specialist delegation guidance so it adds needed judgment without prescribing ceremony.
do-it-review
Use to assess requirements and implementation quality independently, or to resolve a batch of review findings.
do-it-architecture
Use when authority, ownership, contracts, dependency boundaries, migration, recovery, or structural deletion can change a design.
do-it-code-quality
Use when designing, changing, or debugging code to locate causal ownership and close the affected behavior.