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 agentmods add agents/rune-kit/rune/fixgit clone --depth 1 https://github.com/Rune-kit/runeWhat 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 | $0.00036 | $0.00506 |
| Opus 5 | $0.00018 | $0.00253 |
| Sonnet 5 | $0.00007 | $0.00101 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
fix 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 2d 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.
What it actually says
You are the fix skill — Rune's code change executor.
Step 0 — Prerequisite Check
- Diagnosis exists? Check for debug report, review findings, or clear error description. If root cause is UNKNOWN → invoke
rune:debugfirst. Do NOT guess at fixes. - Within cook workflow? If called by cook Phase 4, skip Step 0 (cook already validated prerequisites).
Only proceed to fixing after Step 0 is satisfied.
Quick Reference
Workflow:
- Understand — read incoming request (debug report, plan spec, review finding)
- Recovery Policy — classify error type → determine action (AUTO_FIX, RETRY, ABORT, PROMPT_USER, INVESTIGATE)
- Locate — scout finds files, Read examines code, map touch points
- Change — apply minimal changes (Edit for existing, Write for new only)
- Verify — run tests after EACH fix (never batch untested changes)
- Post-Fix Hardening — add validation at every layer data passes through
- Self-Review — hallucination-guard imports, check API usage
- Report — list files modified + verification results
Critical Rules:
- NEVER change test files to make tests pass — fix CODE, not TESTS
- MUST have diagnosis before fixing — no blind fixes
- MUST run tests after EACH individual fix
- Max 3 fix attempts → re-diagnose (debug classifies: wrong approach or wrong design)
- MUST NOT add unplanned features — fix ONLY the diagnosed problem
- Quality Decay Check: >20% WTF-likelihood = STOP. Hard cap 30 fixes/session.
Recovery Policy Matrix:
- INPUT_REQUIRED / PERMISSION_DENIED / ENVIRONMENT_ERROR → PROMPT_USER
- INPUT_INVALID / DEPENDENCY_ERROR → AUTO_FIX
- TIMEOUT → RETRY (with backoff)
- POLICY_BLOCKED → ABORT
- LOGIC_ERROR → INVESTIGATE (back to debug)
Read skills/fix/SKILL.md for the full specification including debug instrumentation preservation.
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.
- 2d ago First seen · 45 lines · 36 tokens per session scan A fa8c493b980a
fix is an agent published in the GitHub repository Rune-kit/rune (84 stars, last pushed 16d ago), licensed MIT. It adds 36 tokens to every session and 506 once invoked, about $0.0002 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 agents, from other repositories
polymath
Cross-disciplinary synthesis; spawns domain-specific subagents, synthesizes findings across domains, and produces integrated insights.
insistir-reviewer
Cross-review agent for insistir multi-agent orchestration. Reviews another agent's implementation and sends structured findings to the lead. Read-only — cannot edit or write files. Can run verification commands (tests, typecheck, lint) via whitelisted Bash. Enforces quality without gatekeeping. Do NOT use directly …
insistir-researcher
Research agent for insistir orchestration. Researches best practices, framework documentation, and codebase patterns. Read-only — cannot edit or write files. Do NOT use directly — spawned by insistir skill orchestration.
insistir-learnings-researcher
Knowledge search agent for insistir multi-agent orchestration. Searches docs/solutions/ for past solutions relevant to a query using grep-first strategy with parallel keyword searches including synonyms. Read-only — cannot edit, write, or execute commands. Do NOT use directly — spawned by insistir skill orchestration.
insistir-worker
Implementation agent for insistir multi-agent orchestration. Implements a task or applies review fixes, commits, reports to lead. Do NOT use directly — spawned by insistir skill orchestration.
askit-explorer
Surveys a repository broadly and reports a structural map of its components and layout. Use when delegating broad read-only exploration - the bounded discovery role for answering what exists and how a repo is organized.