Borrowing it
Nothing to install: this file belongs to CRJFisher/ariadne. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/CRJFisher/ariadne/main/.claude/skills/self-repair-pipeline/SKILL.mdgit clone --depth 1 https://github.com/CRJFisher/ariadneWrote 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/crjfisher/ariadne/self-repair-pipeline)<a href="https://agentmods.dev/skills/crjfisher/ariadne/self-repair-pipeline"><img src="https://agentmods.dev/badge/skills/crjfisher/ariadne/self-repair-pipeline/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/crjfisher/ariadne/self-repair-pipeline"><img src="https://agentmods.dev/badge/skills/crjfisher/ariadne/self-repair-pipeline.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 | $0.00057 | $0.02776 |
| Opus 5 | $0.00028 | $0.01388 |
| Sonnet 5 | $0.00011 | $0.00555 |
| Haiku 4.5 | $0.00006 | $0.00278 |
Grade A, and why
self-repair-pipeline 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 12d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Repair Pipeline
Triage pipeline for entry point analysis: detect false positives, classify root causes, plan fixes, and create backlog tasks. Supports both self-analysis (Ariadne packages) and external codebase analysis.
Pipeline Overview
| Phase | Script / Agent | Purpose |
|---|---|---|
| 1. Detect | scripts/detect_entrypoints.ts |
Run entry point detection |
| 2. Prepare | scripts/prepare_triage.ts |
Classify against known-entrypoints registry, build triage state |
| 3. Triage Loop | triage-investigator, triage-aggregator, triage-rule-reviewer | Investigate pending entries, aggregate results, review for patterns |
| 4. Fix Planning | fix-planner, plan-synthesizer, plan-reviewer, task-writer | Generate competing fix plans, synthesize, review, create tasks |
| 5. Finalize | scripts/finalize_triage.ts |
Save results, update registry |
Analysis Target
User input: $ARGUMENTS
Resolve the analysis target from the user's input using this routing table:
| Input pattern | Example | Action |
|---|---|---|
| Empty or blank | /self-repair-pipeline |
List available configs below, ask user what to analyze |
| Config name | core, mcp, types, projections |
Use --config .claude/skills/self-repair-pipeline/project_configs/{name}.json |
| Absolute or relative directory path | /Users/chuck/workspace/some-repo, ../other-repo |
Use --path <path> |
owner/repo or GitHub URL |
anthropics/sdk-python, https://github.com/owner/repo |
Use --github <value> |
| Natural language | "analyze the core package" | Interpret intent and map to one of the above |
What ships with it
33 files 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.
- .gitignore 108 B
- examples/sample_triage_output.json 2.5 KB
- package.json 1.0 KB
- project_configs/core.json 158 B
- project_configs/mcp.json 142 B
- project_configs/types.json 146 B
- reference/diagnosis_routes.md 3.6 KB
- reference/state_machine.md 3.8 KB
- scripts/detect_entrypoints.ts 16 KB runs code
- scripts/finalize_triage.ts 3.9 KB runs code
- scripts/prepare_triage.ts 3.5 KB runs code
- scripts/triage_loop_stop.test.ts 22 KB runs code
- scripts/triage_loop_stop.ts 13 KB runs code
- src/analysis_io.ts 2.0 KB runs code
- src/build_finalization_output.test.ts 11 KB runs code
- src/build_finalization_output.ts 3.0 KB runs code
- src/build_triage_entries.test.ts 4.4 KB runs code
- src/build_triage_entries.ts 1.8 KB runs code
- src/classify_entrypoints.test.ts 4.4 KB runs code
- src/classify_entrypoints.ts 1.2 KB runs code
- src/extract_entry_points.test.ts 6.6 KB runs code
- src/extract_entry_points.ts 14 KB runs code
- src/known_entrypoints.test.ts 6.6 KB runs code
- src/known_entrypoints.ts 3.7 KB runs code
- src/paths.ts 533 B runs code
- src/triage_state_types.ts 2.6 KB runs code
- src/types.ts 4.3 KB runs code
- templates/backlog_task_template.md 1.8 KB
- templates/prompt_callers_not_in_registry.md 3.1 KB
- templates/prompt_generic.md 3.6 KB
- templates/prompt_resolution_failure.md 3.7 KB
- templates/prompt_wrong_target.md 3.8 KB
- tsconfig.json 511 B
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.
- 12d ago First seen · 246 lines · 57 tokens per session scan A 7942930d5bdd
self-repair-pipeline is a skill published in the GitHub repository CRJFisher/ariadne (22 stars, last pushed 9d ago), licensed MIT. It adds 57 tokens to every session and 2,776 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 2026-08-30.
Other skills, from other repositories
sem
Use sem to get entity-level (function/class/method) semantic diffs, impact analysis, blame, and dependency context from any Git repo. Trigger this skill whenever the user asks what changed in a commit or PR, wants to understand the blast radius of a change, needs to know who last modified a function, wants to trace…
sem
Semantic version control CLI. Entity-level diffs for Git (functions, classes, methods instead of lines).
ensemble-beads-build
Drive an existing bead hierarchy to completion through the full builder, code-review, and close pipeline (Codex skill for /ensemble:beads-build).
code-review
Reviews diffs for correctness, style, and Bazel wiring before approving.
pr-review
This intentionally has a vague description for audit output.
wayfinder
Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.