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 aeonfun/aeon --skill skill-repairgit clone --depth 1 https://github.com/aeonfun/aeonWrote 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/aeonfun/aeon/skill-repair)<a href="https://agentmods.dev/skills/aeonfun/aeon/skill-repair"><img src="https://agentmods.dev/badge/skills/aeonfun/aeon/skill-repair/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/aeonfun/aeon/skill-repair"><img src="https://agentmods.dev/badge/skills/aeonfun/aeon/skill-repair.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Prompt Injection · line 14 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Rogue Agent · line 232 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00028 | $0.04060 |
| Opus 5.5 | $0.00011 | $0.01624 |
| Sonnet 5.5 | $0.00006 | $0.00812 |
| Haiku 4.5 | $0.00003 | $0.00406 |
Grade A, and why
skill-repair scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`gh` and `git` handle auth internally, so the diagnostic reads carry no `$SECRET` on the command line. There is no network sandbox — `curl` works; use `gh api` for GitHub reads, and prefer **WebFetch** over `curl` for an Copies of this mod
2 near-identical copies found in the catalogue:
- skill-repair — 100% identical, 0 lines differ
- skill-repair — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
${var} — Skill name to repair. If empty, runs systemic triage and picks the worst fixable target.
${var}modifiers: prefixdry-run:to diagnose only without writing a PR (e.g.dry-run:digest).
Today is ${today}. Your task is to diagnose and repair the worst-impact failing or degraded skill — preferring a single shared fix over N per-skill patches when failures cluster.
Phases
PREFLIGHT → TRIAGE → DIAGNOSE → REPAIR → VERIFY → LOG
Stop early at the appropriate exit code if any phase finds nothing actionable.
Exit taxonomy
Pick exactly one before notifying.
| Code | Meaning |
|---|---|
REPAIR_OK_FIXED |
Per-skill fix applied, PR opened |
REPAIR_OK_SYSTEMIC |
Shared root cause across N skills — single shared fix or shared issue filed |
REPAIR_DIAGNOSED_NO_FIX |
Root cause known but requires operator action (e.g. missing secret, upstream API down). Issue updated, no PR |
REPAIR_NO_TARGETS |
All tracked skills healthy and no open fixable issues |
REPAIR_DRY_RUN |
var=dry-run:NAME — diagnostic only, no PR |
REPAIR_BLOCKED |
Preflight failed (gh auth, missing files) or cooldown active |
1. PREFLIGHT
Bail early with REPAIR_BLOCKED (and notify with the reason) if any of these fails:
gh auth statussucceeds.memory/cron-state.jsonexists and parses as JSON.memory/issues/INDEX.mdexists. If absent, bootstrap a minimal one (Open + Resolved tables, no rows).memory/state/skill-repair-history.jsonexists. If absent, create{}.
Cooldown / idempotency (skip target with REPAIR_BLOCKED if any matches; don't loop on a fix that didn't take):
- The chosen target appears in
memory/state/skill-repair-history.jsonwithlast_repair_atwithin 24h. (Operator can override by deleting the entry.) - An open PR already exists matching
fix/skill-repair-{name}-*—gh pr list --state open --search "head:fix/skill-repair-{name}". - More than 3 skill-repair PRs already opened in the current UTC day — rate-limit our own PRs.
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.
- 14d ago Changed 9985be3e5d36
- 1mo ago First seen · 266 lines · 28 tokens per session scan A 25d7ec4b7c05
skill-repair is a skill published in the GitHub repository aeonfun/aeon (782 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 4,060 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
skill-audit
Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review. Use when: AUTOMATICALLY ACTIVATE when user requests auditing:. "audit and check the entire app". "audit X for Y" or "check for broken features".
python-code-quality
Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
triage-issue
Analyze a GitHub issue, verify claims against the codebase, and close invalid issues with a technical response.
hive.error-recovery
Follow a structured recovery decision tree when tool calls fail instead of blindly retrying or giving up.
oracle
Oracle second-model review: bundle prompts/files, debug, refactor, design.