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 skills add rbah31/claude-code-workflow --skill fixgit clone --depth 1 https://github.com/rbah31/claude-code-workflowWrote 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/skills/rbah31/claude-code-workflow/fix)<a href="https://agentmods.dev/skills/rbah31/claude-code-workflow/fix"><img src="https://agentmods.dev/badge/skills/rbah31/claude-code-workflow/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/skills/rbah31/claude-code-workflow/fix"><img src="https://agentmods.dev/badge/skills/rbah31/claude-code-workflow/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 | $0.00083 | $0.01140 |
| Opus 5.5 | $0.00033 | $0.00456 |
| Sonnet 5.5 | $0.00017 | $0.00228 |
| Haiku 4.5 | $0.00008 | $0.00114 |
Grade A, and why
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 1mo 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix Phase
You are running the fix phase. Your job is to fix all issues the human marked as "fix" in the review output — efficiently and correctly.
Step 1 — Load context
Read the triaged review output: tasks/sprints/sprint-*/review-output.md.
Read tasks/lessons.md — avoid repeating past fix mistakes.
Identify all items marked as "fix" (or "critical" / "major" that weren't explicitly deferred).
Step 2 — Fix issues
For each issue to fix:
- Understand the issue — read the finding, the file, and the context.
- Plan if complex — if the fix touches 3+ files, switch to plan mode first to design the approach.
- Implement the fix — make the minimal change that resolves the issue. Don't refactor unrelated code.
- Run tests — verify the fix works and doesn't break anything else.
- Document — note what you did in the fix output.
If a fix introduces a new issue or breaks something: stop, assess, and fix the regression before moving on.
Investigation-shaped findings cannot be deferred
If a review finding requires a quick investigation to diagnose
(a grep to confirm a code path exists, a read to verify the
production shape of an input, a 5-second check on whether a function
already handles the case), do that investigation now — not later.
Specifically: do not mark such a finding as "deferred to claude -p investigation" during the fix phase. Treat the deferral pattern as an anti-pattern: the investigation it points to is almost always shorter than the deferral message itself.
Decision rule:
- Investigation < 15 minutes (a grep, a read, a short script) → do it inside the current fix phase, before declaring the finding resolved or deferred.
- Investigation ≥ 15 minutes (cross-cutting refactor, semantic ambiguity, requires architectural review) → escalate to the human with explicit scope, do not silently defer.
The deferral pattern hides Critical findings under the guise of "need to investigate", lets the sprint close, and the bug ships. Closing a finding requires either a fix or a deliberate, scope-explicit escalation — never a vague "investigation later".
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.
- 1mo ago First seen · 130 lines · 83 tokens per session scan A 6b140b4ea09f
fix is a skill published in the GitHub repository rbah31/claude-code-workflow (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 83 tokens to every session and 1,140 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
review
Use when a change is built and needs review before its PR, when verify runs and specclaw-review is installed, or when the user asks to review, re-review or run the review loop locally.
rules
Use when setting up specclaw-review in a repo, when the user wants review rules created or improved, or asks what the reviewer should check in this codebase.
review-spec
A workflow for comparing an existing feature specification with the project's review checklist and implementation. It looks for missing requirements, differences between documented screens and actual screens, and lessons from rejected submissions.
next-steps
Have the Product Owner survey the project's current state — shipped features, in-flight work, open findings, standing goals — and propose one concrete next feature ready to hand to /story-time or /spark. Use when the user has no idea in hand and asks "what should we build next", when a loop just closed and the next…
increment
Start the Act phase of the SPARK loop: build the increment strictly following the approved plan, task by task, with progress tracked in the plan. Use after the plan is approved, or to fix findings that came back from /peer-review or /demo-day.
fresh-eyes
Audit a finished diff with fresh eyes. The mechanism is double-blind reconciliation: a subagent that never saw the conversation reads the diff blind and reports what it thinks the change does. The main context — which holds the real intent — compares that blind read against what the work was meant to do. The…