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.
git clone --depth 1 https://github.com/pablomarin/claude-codex-forgeWrote 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/commands/pablomarin/claude-codex-forge/quick-fix)<a href="https://agentmods.dev/commands/pablomarin/claude-codex-forge/quick-fix"><img src="https://agentmods.dev/badge/commands/pablomarin/claude-codex-forge/quick-fix/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/commands/pablomarin/claude-codex-forge/quick-fix"><img src="https://agentmods.dev/badge/commands/pablomarin/claude-codex-forge/quick-fix.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 | $0.00000 | $0.00692 |
| Opus 5.5 | $0.00000 | $0.00277 |
| Sonnet 5.5 | $0.00000 | $0.00138 |
| Haiku 4.5 | $0.00000 | $0.00069 |
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 15d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/quick-fix — Host-Neutral Small-Change Workflow
Use only for a clearly understood, low-risk, non-user-facing change with an obvious focused check.
The change may touch at most three implementation paths; exact release metadata paths README.md
and docs/CHANGELOG.md do not consume that budget. If diagnosis is uncertain, architecture or
product judgment is needed, the behavior is user-facing, the change is high-risk, or the path limit
would be exceeded, stop and use /fix-bug or /new-feature.
Apply the shared Startup boundary before the first workflow step. It is the canonical activation, resume, isolation, and setup-failure contract.
Steps
- Resolve the active host and run
.forge/hooks/lib/workflow-state.sh show(PowerShell: the.ps1twin). Resume only the exact matching active workflow. A new quick fix must start from a cleanquick-fix/<slug>branch whoseHEADequals a distinct named base branch; activate it withworkflow-state.sh activate --host <claude|codex> --workflow quick-fix --task <slug> --base-ref <named-base-branch> --phase diagnosis --next-step '<exact next step>'(or the.ps1twin) before investigation or tracked mutation.HEAD, a raw commit SHA, or the quick-fix branch itself is not a valid activation base. - State the acceptance check and affected paths. If behavior changes, write and observe a focused failing test first; documentation-only corrections use a direct rendered or static check.
- Make the smallest change. If the work stops satisfying the quick-fix eligibility rules, checkpoint
the state and restart it as
/fix-bugor/new-feature; do not stretch the quick-fix boundary. - Run the focused check directly in the main session. Quick-fix dispatches no
code-spec,code-quality,verify-app, orverify-e2erole and creates no candidate-bound final receipt set. - Apply this repository's release policy. In the Forge source repository, every merged change set
bumps exact
MAJOR.MINOR.PATCH, records every change indocs/CHANGELOG.md, and adds README release prose only for material changes. Downstream repositories follow their own policy; never invent or rewrite a downstream.forge/versionas part of application work. - Check the complete diff from the recorded base. It must contain no more than three implementation
paths, plus optional exact
README.mdanddocs/CHANGELOG.mdrelease metadata. Record the direct check result in the workflow checklist and runworkflow-state.sh checkpoint(or the.ps1twin) to record the phase as complete. - Commit normally after the ship hook accepts the validated base and scope. Show any push, PR, or merge mutation and pause for the required human authorization; authorization for one external mutation does not imply another.
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.
- 15d ago Changed · -11 lines a2c3affb7450
- 20d ago Changed · +16 lines ea9b46436b1d
- 1mo ago Changed · -93 lines 83e9b8a4dc26
- 1mo ago First seen · 130 lines · 0 tokens per session scan A 50a183b8186b
quick-fix is a command published in the GitHub repository pablomarin/claude-codex-forge (5 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 692 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.