claudeframework: Skill for Claude Code

.claude/skills/3_fix/SKILL.md

3_fix is a skill for Claude Code from dixus/claudeframework. It costs 27 tokens per session (1,675 once invoked), scanned A, original, MIT.

A repair workflow for addressing problems documented in a code review report.

In plain words
What is it for?
It reads the review and related specifications, fixes issues by severity, checks project commands, and stops when a recurring problem needs user guidance.
Why use it?
It turns review findings into a controlled fix process while keeping changes within the current project requirements and phase.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: model in frontmatter; mentions CLAUDE.md; mentions subagents.

This is dixus/claudeframework's own configuration. It tells Claude Code how to work on claudeframework itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claudeframework configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dixus/claudeframework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dixus/claudeframework/main/.claude/skills/3_fix/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dixus/claudeframework

Made for: Claude Code.

Wrote 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.

agentmods badge for 3_fix

README.md
[![agentmods](https://agentmods.dev/badge/skills/dixus/claudeframework/3_fix/github.svg)](https://agentmods.dev/skills/dixus/claudeframework/3_fix)
Your own site
<a href="https://agentmods.dev/skills/dixus/claudeframework/3_fix"><img src="https://agentmods.dev/badge/skills/dixus/claudeframework/3_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.

agentmods 80×15 button for 3_fix

Your own site · 80×15
<a href="https://agentmods.dev/skills/dixus/claudeframework/3_fix"><img src="https://agentmods.dev/badge/skills/dixus/claudeframework/3_fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,675 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.01675
Opus 5.5 $0.00011 $0.00670
Sonnet 5.5 $0.00005 $0.00335
Haiku 4.5 $0.00003 $0.00168

Measured 1mo ago against content hash 35bfdfbae8dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

3_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.

.claude/skills/3_fix/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fix issues found in a review report.

Steps:

  1. Read CLAUDE.md — note the project's test command, lint command, build command, and typecheck command if listed

  2. If $ARGUMENTS is provided, read .claude/reviews/<name>-review.md. Otherwise read the most recently modified file in .claude/reviews/

  3. If a corresponding spec exists in .claude/specs/, read it too — fixes must stay within the spec's stated requirements a. Phase awareness: if .claude/specs/<name>-phases.md exists, read it. Fixes must stay within the current phase's scope. If a review issue references a requirement that belongs to a later (pending) phase, skip it with "out of scope for current phase" — do not implement it.

  4. Parse the Issues section — work through them in order of severity: critical first, then major, then minor

  5. Circuit breaker: for each issue, check whether it appeared in a previous review of the same spec. If the same issue has recurred across two or more review cycles, flag it as a recurring failure, stop fixing, and escalate to the user with a description of the root cause — do not attempt a third fix for the same problem without user guidance.

  6. Scope gate: only touch files that are explicitly mentioned in the Issues section of the review report. For each issue: read the affected file, understand the problem, then apply a minimal fix — do not refactor, clean up, or improve any code outside those files. Unrelated issues belong in the next review cycle, not this fix cycle.

  7. After fixing all issues, run the project's verify commands in this order (read them from CLAUDE.md, skip any not listed): a. Typecheck b. Lint c. Tests d. Build (if listed)

  8. If any verify step fails, fix those failures too. If a verify step still fails after two fix attempts, stop and escalate to the user — do not loop.

  9. Contract re-check: read the spec's ## Contract section and re-run every item's verify command (from its cwd if set, otherwise the repo root) — the fixes may have broken a criterion that was previously green. For type: e2e items, run against the environment the item's env field names; before any env: local run, probe that the local stack is up — an unreachable stack is a blocker to escalate, not a failed criterion. For manual items, re-confirm the criterion by reading the code. List each item and its status. A non-zero exit is a new critical issue that must be fixed before continuing. (In phased mode, only check the contract ids assigned to the current phase.)

    Do this here rather than leaving it to /ship Step 5: catching a regressed criterion inside the fix cycle costs one re-run, while letting Step 5 catch it costs a whole review/fix cycle.

    If the spec has no ## Contract section (legacy spec), fall back to the previous behaviour: if the spec has a "Validation criteria" section, confirm each criterion is still met after the fixes and list each criterion with its status.

  10. Self-check against review items: before declaring done, re-read the review file and verify each issue one by one: a. For each issue marked in the review, re-read the affected file at the specific line b. Confirm the fix actually addresses the issue described — not just a nearby change c. Check that the fix didn't introduce a new problem in the same area (e.g. breaking an import, changing a signature without updating callers) d. If any issue is NOT actually resolved, fix it now before proceeding This step prevents the common pattern where /3_fix reports "all fixed" but the next /2_review finds the same issues still present.

  11. Spec-anchored check: review whether any fixes diverged from the spec's stated requirements. If they did, do not update the spec — the spec is ground truth. Instead, document the divergence in the report (step 13) and flag it for user decision. Only the user may approve spec changes.

    This applies to the ## Contract with no exceptions. Making a failing verify pass by widening its filter, repointing it at a broader suite, relaxing the criterion, or flipping the item to manual is a spec change disguised as a fix — it is the one edit that silently disables the gate the contract exists to provide. Fix the code so the command passes as written, or escalate the item to the user.

  12. Self-improvement gate: for each fixed issue, ask whether a rule would prevent recurrence. If yes, write it to .claude/context/lessons.md immediately using this format:

Read the full file on GitHub · 80 lines

Changes

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.

  1. 1mo ago Changed · +12 lines 35bfdfbae8dc
  2. 2mo ago First seen · 68 lines · 27 tokens per session scan A b1b6e7c83b85

Subscribe to this mod's changes

3_fix is a skill published in the GitHub repository dixus/claudeframework (10 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 1,675 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

cwv-optimizer

Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…

adobe/skills · 112 tokens

incident-response-incident-response

Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.

rmyndharis/antigravity-skills · 36 tokens

ci-fixer

CI failures - read error, minimal fix, verify.

sipyourdrink-ltd/bernstein · 15 tokens

diagnosing-missing-recordings

Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wants to troubleshoot session replay capture issues for a specific session ID or across their project. Covers SDK diagnostic signals, project settings, sampling…

PostHog/posthog · 76 tokens