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/ignaciomarin402/spec-flow-plugin/spec-fixgit clone --depth 1 https://github.com/IgnacioMarin402/spec-flow-pluginWrote 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/ignaciomarin402/spec-flow-plugin/spec-fix)<a href="https://agentmods.dev/commands/ignaciomarin402/spec-flow-plugin/spec-fix"><img src="https://agentmods.dev/badge/commands/ignaciomarin402/spec-flow-plugin/spec-fix.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.03775 |
| Opus 5 | $0.00016 | $0.01887 |
| Sonnet 5 | $0.00007 | $0.00755 |
| Haiku 4.5 | $0.00003 | $0.00378 |
Grade A, and why
spec-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 4d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Orchestrator for the spec-fix pipeline. Drive the state machine below for the defect in $ARGUMENTS.
This is /spec-flow's smaller sibling, and the difference is deliberate rather than sloppy. A feature is an open question about what the system should do, so it earns a spec, a plan, a review and a milestone map. A defect is a closed question: the system already claims a behaviour and something disagrees with the claim. The whole job is finding out which side is wrong — and that is the triage in step 1, not a planning exercise. So this flow drops the planner and the reviewer entirely, and a fix costs one implementer pass instead of a plan, a review and N milestones.
What it does not drop: the external gate, the spec-trace check, and the archived record of what was decided. Lighter means fewer agents, never less proof.
Phase discipline — reuse the vocabulary, never extend it
You manage phase via .claude/state/phase, exactly as /spec-flow does, and you may only write the values that flow already uses: spec, implement, blocked, done, idle.
This is not a style preference. Every enforcement hook decides whether it is armed by matching that file against a closed set of values — the gate, the write-time linter and the whole-repo command deny all run only on implement, the Opus budget and preflight stand down on idle|done, session-start resets any stale run phase. Each one falls through to "not our business" on a value it does not recognise. So inventing a phase like triage or fix would run this flow with the gate, the write-time linter, the whole-repo command deny and the Opus budget all disarmed at once, and nothing would say so — code written with the gate off looks exactly like code that passed it.
Triage runs under spec (it is spec work: deciding what happens to specs/). Everything from the work order onward runs under implement.
arm-gate and phase-guard back you up here the same way they back up /spec-flow: engaging the implementer arms the gate whether or not you wrote the phase, and done is denied while spec-trace, any extra check the project declares, or an unarchived specflow/<SLUG>/ say otherwise. They are the backstop, not the protocol — keep writing every phase yourself.
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.
- 4d ago First seen · 118 lines · 33 tokens per session scan A 6894121ccd11
spec-fix is a command published in the GitHub repository IgnacioMarin402/spec-flow-plugin (2 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 3,775 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 2026-08-31.
Other commands, from other repositories
specmanager-build
Build one phase of a SpecManager feature's plan via the builder subagent. Stops at the phase boundary; never advances.
chronicle
One-time codebase onboarding — interactively extracts your team's conventions, identifies reference files, and generates CLAUDE.md sections so Claude codes the way your team does. Run once per project.
guide
Interactive guide to fellowship. Walks you through a real task using the structured research-plan-implement flow, then shows you what's next.
pb-week
Show this week's training plan as a visual, print-ready weekly card.
audit-plugin
Audit plugin skills, commands, and agents for structure, size, and naming issues.
release
Release the plugin — bump version across 4 files, then optionally commit, tag, push, and create a GitHub Release.