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 commands/robconery/kolea/quick-fixgit clone --depth 1 https://github.com/robconery/koleaWhat 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 | $0.00021 | $0.00678 |
| Opus 5 | $0.00010 | $0.00339 |
| Sonnet 5 | $0.00004 | $0.00136 |
| Haiku 4.5 | $0.00002 | $0.00068 |
Grade A, and why
quick-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.
This is a copy
100% identical to quick-fix — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
quick-fix
For the trivial stuff: a typo, a reversed condition, a dead try/catch, a
misnamed variable, a stray import. The kind of bug where opening
/explore → /design → /plan → /build-loop would be absurd.
Scope
- IN: one-spot fixes that a competent engineer would commit straight to
mainwithout ceremony. Single concern. Usually < ~20 lines changed. - OUT: anything that needs a design call, touches a public API contract,
changes behavior across modules, or needs new tests beyond what already
exists. If it smells like that, stop and suggest
/planor/build-loop.
Argument
$ARGUMENTS describes the fix in the user's words (e.g. "remove the
unneeded try/catch in fetchUser", "fix the typo in the login button").
If empty, ask one short clarifying question.
Loop
- Locate. Find the exact site. If the description is ambiguous or matches multiple places, ask before guessing.
- Confirm it's actually small. If reading the surrounding code reveals
the fix is non-trivial (touches a class boundary, changes a contract,
needs new branches of test coverage), stop and escalate — tell the
user this isn't a quick-fix and suggest
/plan. - Consult skills selectively. Only load a code-quality skill if the
fix genuinely touches its territory:
solid-principles/design-principles/gof-patterns: only if the fix sits at a class or module boundary, or changes a control-flow pattern. Skip for typos, comments, log strings, dead code removal.agent-teams: skip — quick-fixes are single-threaded by definition.typescript-best-practices: consult if the fix involves types,any/unknown, null handling, or error shape.
- Apply the edit. Use
Edit, notWrite. Match surrounding style. - Verify. Run the project's typecheck and tests if they're fast. If
they're slow or absent, run the narrowest check that proves the fix
(e.g.
tsc --noEmiton the file, or the single related test). - Report and ask before committing. Show the diff summary and propose
a one-line commit message. Do not commit unless the user says go —
committing straight to
mainis a shared-state action.
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 · 63 lines · 21 tokens per session scan A ecebfd994975
quick-fix is a command published in the GitHub repository robconery/kolea (1 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 678 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to quick-fix, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
git-issue
Open a GitHub issue with a clear, detailed body via gh issue create. Uses the github skill.
plan
Slice SPEC into stories and an ordered task DAG. Owns STORIES.md + PLAN.md.
product-intake
Turn raw experience reports from using the product into agent-ready GitHub issues at the right maturity. The user arrives wearing the user hat — "here's what happened when I used the thing" — and shifts to the product hat to make decisions about maturity, framing, and priority.
analyze
Extract project-relevant insights from user-provided input. The user brings material — a session write-up, product feedback, a captured fragment, an error log, a design sketch, a conversation transcript — and you turn it into actionable artifacts: GitHub issues, issue comments, doc updates, ADRs, or memory entries.
work-on-issue
Execute the full planning-before-implementation workflow for a GitHub issue. The user provides an issue number or description — you handle the rest.
quick-fix
Make a small, obvious fix directly on the current branch. No sprint, no PLAN, no stories.