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 ivy00johns/Skill-Madness --skill self-healing-loopgit clone --depth 1 https://github.com/ivy00johns/Skill-MadnessWrote 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/ivy00johns/skill-madness/self-healing-loop)<a href="https://agentmods.dev/skills/ivy00johns/skill-madness/self-healing-loop"><img src="https://agentmods.dev/badge/skills/ivy00johns/skill-madness/self-healing-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/ivy00johns/skill-madness/self-healing-loop"><img src="https://agentmods.dev/badge/skills/ivy00johns/skill-madness/self-healing-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 | $0.00208 | $0.02911 |
| Opus 5 | $0.00104 | $0.01456 |
| Sonnet 5 | $0.00042 | $0.00582 |
| Haiku 4.5 | $0.00021 | $0.00291 |
Grade A, and why
self-healing-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 9d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
self-healing-loop
A configuration of [
loop-controller]. That skill supplies the loop machinery — primitive selection, the full guardrail stack, state externalization. This skill supplies the three things specific to "watch and heal": a poll cadence over an external error signal, a default-FAIL proof of the error gone (a re-run, not a hope), and a hard HITL boundary at any prod-touching or irreversible fix. Readloop-controllerfor the guardrails; they're inherited, not repeated here.Why
disable-model-invocation: this loop edits and commits code on its own and opens PRs on a schedule. You want to type/self-healing-loop(or wire it under/loop) — not have Claude silently start an autonomous heal loop because a log line looked alarming.
The 5-part contract
| Part | This loop |
|---|---|
| trigger | a scheduled poll tick (via /loop) over an error source — red CI, an error-log query, an alert/Channel push — or an explicit /self-healing-loop |
| action | ONE pass: poll the source → triage actionable vs noise → if actionable, reproduce + root-cause (hand the hard diagnosis to [diagnose-loop]) → fix the cause in a branch → verify → open/update a PR; else record a clean-log confirmation |
| proof | the error is resolved AND verified — the re-run of the failing signal now passes / the log query is clean — default-FAIL: assume UNRESOLVED until the re-run proves it. Artifact = the green re-run output (or, on a quiet tick, a timestamped clean-log confirmation) |
| memory | heal_log.md (one entry per tick: signal seen, triage verdict, root cause, the PR opened, the verifying re-run) + the fix branch's git history; the last-seen error fingerprint so a known-open error isn't re-triaged each tick |
| stop | the verifying re-run passes and a PR is open (or the tick is clean) OR iteration cap OR no-progress for N ticks on the same error OR budget cap OR an HITL checkpoint is hit (a prod-touching / irreversible fix) — pause for the human, never proceed |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 196 lines · 208 tokens per session scan A 4d89e4cecb81
self-healing-loop is a skill published in the GitHub repository ivy00johns/Skill-Madness (11 stars, last pushed yesterday), licensed MIT. It adds 208 tokens to every session and 2,911 once invoked, about $0.0010 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 2026-08-30.
Other skills, from other repositories
agent-merge-conflict-arbiter
Neutral arbiter for merge conflicts between two agents.
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
bisect
Bisect regressions or broken builds in the Chromium repository using deterministic binary search, checking out midpoint commits, syncing dependencies with gclient sync, compiling the target with autoninja, and querying the user for test results until the culprit commit is isolated.
mantis-critic
Assesses the production viability of findings, filtering out debug-only features and assertion traps. Use when findings have been validated and you need to confirm they are triggerable in production release builds (with assertions disabled). Don't use for writing reproduction scripts or patches.
hotpath_bump
Bump the hotpath version number across the workspace and related files. Updates crate versions in Cargo.toml files (exact patch version) and version references in the backend middleware, hotpathinit skill, and README (major.minor only). Use when the user wants to bump, bump the version, or release a new hotpath…
comet-github-issue-fix
A workflow for fixing a confirmed Comet-related GitHub issue or review blocker within an isolated scope. It covers matching the work to the relevant workflow, testing the change, checking runtime results, and preparing a careful handoff.