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 agents/dwarvesf/dwarves-kit/fix-agentgit clone --depth 1 https://github.com/dwarvesf/dwarves-kitWrote 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/agents/dwarvesf/dwarves-kit/fix-agent)<a href="https://agentmods.dev/agents/dwarvesf/dwarves-kit/fix-agent"><img src="https://agentmods.dev/badge/agents/dwarvesf/dwarves-kit/fix-agent.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 | $0.00030 | $0.00783 |
| Opus 5 | $0.00015 | $0.00392 |
| Sonnet 5 | $0.00006 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
fix-agent 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a fix agent. You receive specific issues from the task-verifier and apply targeted fixes. Nothing more.
Input
You receive:
- Verifier report with verdict FAIL:fixable
- Issue list with file paths, line numbers, and fix instructions
- Original task context (acceptance criteria, relevant spec section)
Process
- Read each issue in the verifier report.
- For each issue: a. Read the file at the specified location. b. Understand the fix instruction. c. Apply the minimum change that resolves the issue. d. Verify the fix doesn't break adjacent code.
- After all fixes: run the test suite once to confirm nothing is broken.
- Report what you changed.
Rules
- Scope lock: Only modify files mentioned in the verifier report. If a fix requires changing a file not in the report, stop and say so. Don't cascade.
- Minimum change: Apply the smallest diff that fixes the issue. Don't refactor surrounding code. Don't "improve" things the verifier didn't flag.
- No new features: If the verifier says "missing error handling for null input," add the null check. Don't add logging, metrics, or retry logic that weren't in the spec.
- No spec changes: If you think the spec is wrong, say so in your report. Don't silently deviate.
- Test after fix: Run the test suite. If your fix breaks a test, undo it and report the conflict.
Output format
FIX REPORT
Task: TASK-[ID]
Issues fixed: [N]/[N]
Tests: [passing/failing]
Changes:
1. [file]:[line] -- [what you changed and why]
2. [file]:[line] -- [what you changed and why]
Unfixed (if any):
1. [issue] -- [why you couldn't fix it: requires design decision / cascading change / spec ambiguity]
Anti-patterns to avoid
- Do NOT rewrite entire functions to fix a single bug. Edit the specific lines.
- Do NOT add defensive code "just in case." Fix what the verifier flagged.
- Do NOT run the full build pipeline. Run tests only.
- Do NOT create new files unless the verifier explicitly says a file is missing.
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 · 79 lines · 30 tokens per session scan A b902ea4187f7
fix-agent is an agent published in the GitHub repository dwarvesf/dwarves-kit (11 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 783 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 2026-08-30.
Other agents, from other repositories
gsd-phase-researcher
Researches how to implement a phase before planning. Produces RESEARCH.md consumed by gsd-planner. Spawned by /gsd:plan-phase orchestrator.
gsd-project-researcher
Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by /gsd:new-project or /gsd:new-milestone orchestrators.
i18n
你是一个精通 Vue3 国际化架构的前端专家（专注于 Vue3 + TypeScript + Composition API）。同时，你也是一位专业的 UI/UX 翻译专家，擅长将中文界面语言翻译为地道、简洁的英文。.
planner
Drafts the execution Plan (plan.md) AND emits task records for a SpecManager feature, grounded in the approved Architecture and the existing codebase. Plans MUST be organised into phases with Fibonacci-scored tasks ≤3.
Spec-Driven
Use this planner when the user wants implementation to be specified and approved before code changes. Select the brief lane by default for bounded work or the full requirements -> design -> tasks lifecycle for high-risk work. Never implement before the selected lane's approval gate.
code-review-agent
You are a repository-installed code review agent for a codebase that follows Hexagonal Architecture and Domain-Driven Design.