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/oreum-ai/smartstack/debug-fixnpx skills add oreum-ai/smartstack --skill debug-fixgit clone --depth 1 https://github.com/oreum-ai/smartstackWhat 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 | $0.00000 | $0.00464 |
| Opus 5 | $0.00000 | $0.00232 |
| Sonnet 5 | $0.00000 | $0.00093 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
debug-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 yesterday.
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
Skill: Debug & Fix
When to use
The moment something breaks: a crash, a failed request, a wrong value, a red test, a confusing bug. This is the skill that makes the error ledger pay off.
The order matters — check memory before inventing
- Common errors (terse, permanent). Open
ai-rules/memory/errors/common-errors.md. Scan the short entries by index (symptom → cause → fix). If it matches, apply that fix. - Recent errors (detailed, last few). Open
ai-rules/memory/errors/recent-errors.md. Did we hit this exact thing recently? If so, apply the recorded solution. - Only if no match — diagnose fresh (below).
Doing this first saves tokens and stops you re-solving the same bug. Use the index; don't re-read all history.
Fresh diagnosis (only when the ledger has no match)
- Reproduce. Get the exact error text and the steps that trigger it. Don't guess from a description.
- Read the real code. Open the file(s) involved and read the relevant section before changing anything.
- Add one targeted log at the decision point to confirm actual values. Confirm the hypothesis with data.
- Fix the root cause, not the symptom. A guard that hides a wrong value isn't a fix — ask why it's wrong.
- Verify. Re-run; confirm the failure is gone and nothing else broke (lint/build/tests).
- Remove the temporary log once fixed (unless it's worth keeping while the bug might recur).
Record it (always, when the bug was non-trivial)
- Run
ai-rules/scripts/error-log.shto append torecent-errors.md: symptom, root cause, fix, file. - If it's a recurring class, add a short entry to
common-errors.md(a few lines, kept forever).
Why this works
Most bugs repeat in shape. A small, indexed memory of "symptom → cause → fix" turns a 30-minute re-diagnosis into a 30-second lookup — and keeps token spend low.
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.
- yesterday First seen · 31 lines · 0 tokens per session scan A ff2b7f1a2fa4
debug-fix is a skill published in the GitHub repository oreum-ai/smartstack (5 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 464 tokens. 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…