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 skills/d-oit/rust-2026-template/self-fix-loopnpx skills add d-oit/rust-2026-template --skill self-fix-loopgit clone --depth 1 https://github.com/d-oit/rust-2026-templateWhat 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 | $0.00081 | $0.01160 |
| Opus 5 | $0.00041 | $0.00580 |
| Sonnet 5 | $0.00016 | $0.00232 |
| Haiku 4.5 | $0.00008 | $0.00116 |
Grade A, and why
self-fix-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Fix Loop Skill
When to Use
- User asks for this skill's functionality
Automated self-learning cycle: commit → push → monitor → analyze failures → fix → retry until all CI checks pass.
Self-Fix Threshold: If 2+ similar errors occur during the loop, pause and diagnose the root cause before attempting another fix.
Overview
Continuous improvement loop that:
- Commits all changes atomically
- Pushes to feature branch
- Creates/updates PR/MR
- Monitors CI (GitHub Actions or GitLab CI)
- On failure: diagnoses and fixes
- Repeats until ALL checks pass
Platform Detection
Auto-detect from git remote:
REMOTE=$(git remote get-url origin)
if echo "$REMOTE" | grep -qi "github"; then
PLATFORM="github"; CLI="gh"
elif echo "$REMOTE" | grep -qi "gitlab"; then
PLATFORM="gitlab"; CLI="glab"
fi
CLI Command Mapping
| Action | GitHub (gh) |
GitLab (glab) |
|---|---|---|
| Check CI | gh pr checks |
glab ci status |
| Create PR/MR | gh pr create |
glab mr create |
| View logs | gh run view --log-failed |
glab ci view |
Arguments
| Argument | Description | Default |
|---|---|---|
--max-retries N |
Maximum fix iterations | 5 |
--platform github|gitlab |
Force platform | auto-detect |
--auto-research |
Use web research on failures | true |
--fix-issues |
Attempt automatic fixes | true |
--strict-validation |
ALL checks must pass | true |
--timeout SECONDS |
Per-iteration timeout | 1800 |
--dry-run |
Simulate without pushing | false |
Loop Phases
[Start]
↓
Phase 1: COMMIT & PUSH
- Stage all changes
- Run quality gate
- Atomic commit
- Push to feature branch
↓
Phase 2: CREATE/UPDATE PR/MR
- Create new PR/MR or update existing
↓
Phase 3: MONITOR CI
- Poll GitHub Actions / GitLab CI
- Wait for all checks complete
↓
Phase 4: ANALYZE FAILURES
- Identify failed checks
- Extract error messages
- Categorize failure type
↓
Phase 5: FIX (if failures)
- Diagnose root cause
- Apply fixes
- Commit fix
↓
Phase 6: RETRY LOOP
- If retries remaining → Phase 1
- If max retries → FAIL
- If all pass → SUCCESS
What ships with it
1 file 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.
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 · 141 lines · 81 tokens per session scan A 3ffcd360bd26
self-fix-loop is a skill published in the GitHub repository d-oit/rust-2026-template (10 stars, last pushed 3d ago), licensed MIT. It adds 81 tokens to every session and 1,160 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
jamjet-durability-patterns
Production durability patterns for AI agents on the JVM — crash recovery, audit trails, human-in-the-loop, and replay testing using JamJet runtime.
review-backend
Performs a strict code review of Rust backend code (files, diffs, or snippets). Trigger whenever the user shares backend code (Rust, SQL) and asks for a review, feedback, or says "review this" — including partial snippets.
yada-yada-yada
Enter Seinfeld Mode. Explain programming, debugging, architecture, and code reviews through observational comedy inspired by Seinfeld. Trigger when the user says "what's the deal", festivus, serenity, yada, soup, shrinkage, sponge-worthy, master of my domain, double dip, newman, vandelay, nostrand, constanza or…
fix-issue
Fixes a bug, implements a missing feature, or implements one slice of a larger feature, starting from a GitHub issue link, number, or direct text description. Trigger when the user gives a GitHub issue URL/reference/description and asks to fix, implement, resolve, or work on it.
review-frontend
Performs a strict code review of the Svelte 5 frontend code (files, diffs, or snippets). Trigger whenever the user shares frontend code (Svelte, TypeScript, CSS) and asks for a review, feedback, or says "review this" — including partial snippets.
make-it-so
Enter Star Trek command mode. Use Star Trek terminology naturally while remaining a highly competent engineering officer. Trigger when the user mentions Star Trek, Picard, make it so, engage, stardate, number one, federation, borg, warp, enterprise.