Borrowing it
Nothing to install: this file belongs to opendatahub-io/autofix-skills. 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/opendatahub-io/autofix-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/opendatahub-io/autofix-skillsWrote 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/instructions/opendatahub-io/autofix-skills/agents-md)<a href="https://agentmods.dev/instructions/opendatahub-io/autofix-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/opendatahub-io/autofix-skills/agents-md/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/instructions/opendatahub-io/autofix-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/opendatahub-io/autofix-skills/agents-md.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 | $0.01168 | $0.01168 |
| Opus 5.5 | $0.00467 | $0.00467 |
| Sonnet 5.5 | $0.00234 | $0.00234 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
autofix-skills AGENTS.md 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 4d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
autofix-skills
Orchestrator skills, prompt files, and state scripts for the Jira autofix pipeline. This repository is the inner layer. Ticket fetching, repo cloning, container launch, verdict reading, push, and labeling live in jira-autofix and agentic-ci.
Navigation
Detailed context is organized in the .agents/ tree. Start here for shared
rules, then follow the path matching your task.
Read .agents/README.md to find a task guide or portable
skill. The guidance is tool-neutral and applies to any coding agent.
- When adding or changing a skill, its prompts, schemas, or scripts, see
.agents/skills-authoring/README.mdand theautofix-skillsskill - When investigating an agent-side failure, use the
debug-autofix-skillsskill
Skills
| Skill | What it does |
|---|---|
autofix-resolve |
Implement, review, and evaluate loop for a bug ticket |
autofix-cve-resolve |
CVE remediation state machine across repos |
autofix-triage |
Bug readiness verdict: ready, needs_info, or not_fixable |
autofix-repo-resolve |
Pick the target repo when a ticket lists several URLs |
Pipeline skills stay in skills/. The plugin installer discovers skills/,
.claude/skills/, and .opencode/skills/. The marketplace entry for this
plugin sets no skills path.
Architecture
autofix-resolve and autofix-cve-resolve dispatch sub-agents through prompt files and delegate deterministic work to Python scripts. Prompts and scripts hold the domain logic. The orchestrator dispatches and decides.
Prompt files (prompts/*.md) are self-contained personas for one task: implement a fix, review changes, scan for CVEs, and so on.
Scripts do JSON merging, state persistence, CVE routing, and schema validation. Each skill ships its own scripts/ directory. ${CLAUDE_SKILL_DIR} points to the skill root containing SKILL.md and scripts/. Call scripts with python3 ${CLAUDE_SKILL_DIR}/scripts/<name>.py. write_json.py is a PEP 723 script: uv run --script ${CLAUDE_SKILL_DIR}/scripts/write_json.py. state.py is copied in both autofix-resolve/scripts/ and autofix-cve-resolve/scripts/. Change both copies together.
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.
- 4d ago Changed · -8 lines · -463 tokens per session 881e8a6eb7ff
- 26d ago Changed · +100 tokens per session ecf1e377dadd
- 1mo ago First seen · 88 lines · 1,531 tokens per session scan A fd561694187d
autofix-skills AGENTS.md is an instructions file published in the GitHub repository opendatahub-io/autofix-skills (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,168 tokens to every session, about $0.0047 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.