Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/nguyenthienthanh/aura-frognpx agentmods add skills/nguyenthienthanh/aura-frog/self-healing-orchestratorWrote 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/nguyenthienthanh/aura-frog/self-healing-orchestrator)<a href="https://agentmods.dev/skills/nguyenthienthanh/aura-frog/self-healing-orchestrator"><img src="https://agentmods.dev/badge/skills/nguyenthienthanh/aura-frog/self-healing-orchestrator/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/nguyenthienthanh/aura-frog/self-healing-orchestrator"><img src="https://agentmods.dev/badge/skills/nguyenthienthanh/aura-frog/self-healing-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00069 | $0.01477 |
| Opus 5 | $0.00034 | $0.00739 |
| Sonnet 5 | $0.00014 | $0.00295 |
| Haiku 4.5 | $0.00007 | $0.00148 |
Grade A, and why
self-healing-orchestrator 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 8d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-consumed reference. Optimized for Claude to read during execution. Human-readable explanation: see docs/architecture/HIERARCHICAL_PLANNING.md or docs/getting-started/ depending on topic.
Self-Healing Orchestrator
STATUS — v3.7.0-rc.1. Per-spec safety gates strictly enforced.
Core Principle
Self-healing PROPOSES; the user APPLIES. A proposal goes through the same approval gate as a manual replan — there is no autonomous patch. If you find this skill applying patches without a user yes, that's a bug.
Hard constraints (per spec §22.1)
constraints[6]{rule,enforcement}:
"ONLY F2 (local-logic) or F3 (local-design)","Refuse if classifier returns F1/F4/F5/F6 — those need different paths"
"ONLY proposes; NEVER applies","Output is always a proposal artifact; user runs /aura-frog:heal accept <id> to apply"
"Confidence < 0.7 → don't propose","Surface raw findings only; user decides if a fix is even reachable"
"Counts toward replan_budget","Same node-level budget enforcement as replanner (per replan-thresholds.md)"
"Max 1 self-heal per task","Once a task accepts a self-heal patch, no further auto-proposals for that task"
"Session cap: 5 proposals total","Anti-fatigue + anti-loop; after 5, defer to manual /aura-frog:plan-replan"
Disable mechanisms (per spec §22.3, §31.3)
- Per-session:
/aura-frog:heal disable— sets.claude/logs/.self-heal-disabledflag - Permanent:
AF_SELF_HEAL_DISABLED=truein.envrc - Hook integration ignores any proposal when disabled
Flow (per spec §22.2)
Failure detected (F2 or F3)
↓
self-healing-orchestrator activated (only if budget remaining)
↓
Step 1: Parse error log → error class, library, line numbers
Step 2: Query context7 for known library patterns (NOT random web sources)
Step 3: Cross-reference permanent_memory.md "Gotchas discovered"
Step 4: Generate PROPOSED patch as draft (diff format, not applied)
Step 5: Score confidence: refuse if < 0.7
Step 6: Master-planner presents user prompt with diff + reasoning + confidence
Step 7: On user yes → apply as a NEW T4 task with its own approval flow
Step 8: On user no → log as `event: self_heal_declined`, increment session counter
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.
- 8d ago First seen · 113 lines · 69 tokens per session scan A bd306cf85206
self-healing-orchestrator is a skill published in the GitHub repository nguyenthienthanh/aura-frog (24 stars, last pushed 7d ago), licensed MIT. It adds 69 tokens to every session and 1,477 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
biome
Biome formatting and linting standards. Use when configuring Biome (biome.json) for fast formatting, linting, and sorting imports. NOT for Prettier or ESLint configuration. Do NOT trigger for generic formatting/linting tasks unless Biome is explicitly requested.
adversarial-performance
Multi-pass adversarial performance audit for entire repositories. Combines structured profiling (Agent A) with adversarial stress-testing critique (Agent B) through iterative passes. Optimize repo/backend performance, hot-paths, build size, and server throughput. Do NOT use for frontend page load metrics or Lighthouse…
autonomous-dev
Harness for autonomous software development. Use when fixing or remediating known issues (including security vulnerabilities). Enforces lifecycle through alignment gates (PROJECT.md), adversarial generator/evaluator agents, and autonomous orchestration of project issues. NOT for setting up standalone CI/CD pipelines.
debugger-coordinator
Use when debugging complex issues involving multiple modalities (frontend + backend, API + UI, terminal + browser). Coordinates Hermes Agent's built-in debugger, browser, terminal, and vision tools for systematic root-cause analysis.
gsd-debug
Systematic debugging with persistent state across context resets.
gsd-ns-review
Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.