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/marcusgoll/spec-flow/fix-cigit clone --depth 1 https://github.com/marcusgoll/Spec-FlowWrote 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/marcusgoll/spec-flow/fix-ci)<a href="https://agentmods.dev/commands/marcusgoll/spec-flow/fix-ci"><img src="https://agentmods.dev/badge/commands/marcusgoll/spec-flow/fix-ci.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 | $0.00018 | $0.03765 |
| Opus 5 | $0.00009 | $0.01883 |
| Sonnet 5 | $0.00004 | $0.00753 |
| Haiku 4.5 | $0.00002 | $0.00377 |
Grade A, and why
fix-ci 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 3d 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 — 638 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fix-ci — CI Blocker Resolution
Current Branch: !git branch --show-current 2>/dev/null || echo "none"
PR from Current Branch: !gh pr list --head $(git branch --show-current 2>/dev/null) --json number,title,state -q '.[0]' 2>/dev/null || echo "null"
GitHub CLI: !gh auth status 2>&1 | head -1 || echo "not authenticated"
Git Status: !git status --short | head -5
Mission: Act as a deployment doctor — diagnose, auto-fix, delegate, validate.
What This Command Does:
- Load PR context (checks, files, reviews)
- Categorize failures (lint, types, tests, build, deploy)
- Auto-fix simple issues (formatting, linting)
- Delegate complex issues to specialist agents
- Validate deployment readiness
Risk Level: MEDIUM — May push auto-fix commits to PR branch
- Never claim fixes without verification — Run commands, check exit codes
- Quote real CI output — Use
gh pr checksfor actual errors - Read PR diff first — Don't guess root cause without evidence
- Verify check status — Poll
gh pr checksafter pushes - No fabricated URLs — Only report URLs from actual CI logs
Step 1: Parse PR Number
If argument provided: Use it as PR number If no argument: Detect from current branch
# Get PR number from current branch
gh pr list --head $(git branch --show-current) --json number -q '.[0].number'
If no PR found: Show usage and exit
Usage: /fix-ci <pr-number>
Example: /fix-ci 123
Or run from a branch with an open PR.
Step 2: Load PR Context
Fetch PR data:
gh pr view $PR_NUMBER --json title,baseRefName,headRefName,state,mergeable,reviewDecision,files
Extract:
PR_TITLE— PR titlePR_BASE— Base branch (main, production, etc.)PR_HEAD— Head branch (feature branch)PR_STATE— State (OPEN, MERGED, CLOSED)PR_MERGEABLE— Merge statusPR_REVIEW— Review decision (APPROVED, CHANGES_REQUESTED, etc.)
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.
- 3d ago First seen · 638 lines · 18 tokens per session scan A 51e85aa3da4b
fix-ci is a command published in the GitHub repository marcusgoll/Spec-Flow (91 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 3,765 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
review
Review the current diff for violations of the conventions in AGENTS.md and .cursor/rules/. Report findings ordered by severity; do not fix anything unless asked.
task-verify
PitWay: Run an inprogress task's approved verification command and persist evidence.
milestone-list
PitWay: List every milestone with a concise one-line status.
adv-gemini-research
Deep research query via Gemini with Google Search grounding.
vd-arch-review
Audita arquitetura de código em 3 níveis (macro/meso/micro). Detecta separação de camadas, anti-patterns, vazamento de abstração, dependências externas vs código customizado, acoplamento. User-invoked, sob demanda, para devs (não leigo). Use quando o usuário pede "auditoria arquitetural", "code review arquitetural"…
example
Example command that demonstrates CodexSpec extension functionality.