agent-feed: Skill for Claude Code

.agents/skills/project-fix/SKILL.md

project-fix is a skill for Claude Code, Codex from fqmyysjjd/agent-feed. It costs 28 tokens per session (306 once invoked), scanned A, original, MIT.

A software-fix workflow for bugs, failed tests, regressions, merge issues, and inconsistent behavior. It guides investigation, minimal changes, testing, and verification.

In plain words
What is it for?
Use it to reproduce bugs, fix review findings, resolve contract drift, update tests, and verify behavior.
Why use it?
It helps trace a defect to its cause and fix it without unnecessarily changing unrelated parts of a project.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is fqmyysjjd/agent-feed's own configuration. It tells Claude Code and Codex how to work on agent-feed 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 agent-feed configures →

Reuse

Borrowing it

Nothing to install: this file belongs to fqmyysjjd/agent-feed. 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/fqmyysjjd/agent-feed/main/.agents/skills/project-fix/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/fqmyysjjd/agent-feed

Made for: Claude Code, Codex.

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 project-fix

README.md
[![agentmods](https://agentmods.dev/badge/skills/fqmyysjjd/agent-feed/project-fix.svg)](https://agentmods.dev/skills/fqmyysjjd/agent-feed/project-fix)
Your own site
<a href="https://agentmods.dev/skills/fqmyysjjd/agent-feed/project-fix"><img src="https://agentmods.dev/badge/skills/fqmyysjjd/agent-feed/project-fix.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 306 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00028 $0.00306
Opus 5 $0.00014 $0.00153
Sonnet 5 $0.00006 $0.00061
Haiku 4.5 $0.00003 $0.00031

Measured 6d ago against content hash ca64bb2348ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

project-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 6d 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.

.agents/skills/project-fix/SKILL.md · 35 lines

What it actually says

Project Fix Skill

Required Use

Use this skill for bug fixes, review finding fixes, regression fixes, failed test fixes, merge conflict aftermath, contract drift, or behavior inconsistencies.

Required Reading

  1. .agents/rules/outcome-boundary.md
  2. .agents/skills/project-architecture/SKILL.md
  3. .agents/skills/engineering-planning/SKILL.md
  4. .agents/skills/project-development/SKILL.md
  5. .agents/rules/review-gates.md
  6. .agents/rules/testing-gates.md
  7. .agents/domain/contracts.md

Workflow

  1. Recover the current task result boundary.
  2. Use .agents/skills/engineering-planning/SKILL.md to decide owner, reuse, placement, write set, boundaries, and verification before editing.
  3. Intake symptom, expected behavior, current behavior, changed files, and affected phase.
  4. Reproduce or trace the issue.
  5. Locate the root cause and owner module.
  6. Apply the smallest fix that preserves boundaries and source-of-truth ownership.
  7. Add or update tests that would fail before the fix and pass after it when practical.
  8. Run relevant verification.
  9. Stop when the declared fix boundary is satisfied.
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. 6d ago First seen · 35 lines · 28 tokens per session scan A ca64bb2348ce

Subscribe to this mod's changes

project-fix is a skill published in the GitHub repository fqmyysjjd/agent-feed (4 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 306 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 2026-08-31.

Related

Other skills, from other repositories

bug-capture

Capture a user-reported defect as a durable GitHub issue written in the project's own domain language. Explores the codebase in parallel for context but never leaks file paths or line numbers into the issue. Use when the user reports a bug conversationally, runs a QA pass, or says "file an issue", "log this as a bug"…

rohitg00/pro-workflow · 78 tokens

dxkit-flow

Configure, diagnose, and repair the dxkit UI→API integration gate — set up flow gating, explain the flow-contract diagnosis, fix a net-new broken integration a guardrail flagged, and run the cross-repo handshake. Use when the user says "set up the flow gate", "why is this call unresolved", "the guardrail says I broke…

vyuh-labs/dxkit · 112 tokens

incident-triage-harness

Production-style incident triage workflow for logs, metrics, code, safe mitigations, and M3 multimodal visual evidence (screenshots, screen recordings). Use when debugging alerts, regressions, outages, or suspicious runtime behavior.

madebyaris/advance-minimax-m3-cursor-rules · 53 tokens

bughunter

When the user wants to find bugs, test edge cases, stress-test code, or perform adversarial analysis of their codebase. Use when the user says "find bugs," "break this," "what could go wrong," "red team," "hunt bugs," "adversarial test," "edge cases," "stress test," "what did I miss," "pen test this logic," or before…

irfad7/claude-power-skills · 103 tokens

codebase-insight

When the user wants to deeply understand a codebase, map its architecture, or build a persistent mental model for future sessions. Use when the user says "explain this codebase," "map the architecture," "codebase insight," "understand this repo," "what does this project do," "how does this work," "analyze the…

irfad7/claude-power-skills · 98 tokens

stuck-recovery

When you or the user are going in circles, stuck on a problem, or repeating failed approaches. Use when the user says "I'm stuck," "this isn't working," "we keep going in circles," "try something different," "nothing works," "help," or when you detect that you've attempted the same category of solution 2+ times…

irfad7/claude-power-skills · 90 tokens