fixer

fixer is an agent for Claude Code from flonat/flonat-research. It costs 183 tokens per session (4,012 once invoked), scanned A, original, MIT.

A narrowly directed agent that applies fixes described in a critic’s report. It then recompiles the project and writes a report of what it changed.

In plain words
What is it for?
Use it to apply critical, major, and minor corrections from CRITIC-REPORT.md, verify the result by recompiling, and produce FIX-REPORT.md.
Why use it?
It separates deciding what is wrong from implementing the correction, reducing the chance of unrelated edits or personal interpretation during the fix.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/flonat/flonat-research/fixer
Clone the repo
git clone --depth 1 https://github.com/flonat/flonat-research

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 fixer

README.md
[![agentmods](https://agentmods.dev/badge/agents/flonat/flonat-research/fixer.svg)](https://agentmods.dev/agents/flonat/flonat-research/fixer)
Your own site
<a href="https://agentmods.dev/agents/flonat/flonat-research/fixer"><img src="https://agentmods.dev/badge/agents/flonat/flonat-research/fixer.svg" alt="Measured on agentmods" height="20"></a>
Per session 183 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,012 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 $0.00183 $0.04012
Opus 5 $0.00092 $0.02006
Sonnet 5 $0.00037 $0.00802
Haiku 4.5 $0.00018 $0.00401

Measured 4d ago against content hash f733d4408e4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fixer 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 4d 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/agents/fixer.md · 317 lines

How it starts

The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execution contract (generated; mandatory)

  • Project changes are allowed only within the caller-approved scope.
  • Write project files only within the caller-approved scope.
  • Write reports only at the declared artifact path: reviews/<scope>/fixer/<YYYY-MM-DD-HHMM>.md.
  • Do not stage, commit, push, or otherwise mutate Git state.
  • Do not persist agent memory.
  • Declared capabilities: filesystem-read, report-write, scoped-project-write, shell, skill-routing.

Fixer: Precise Fix Implementer

LaTeX source format (prose edits)

Paper prose is one source line per paragraph. When a fix rewrites, inserts, or reflows body prose, leave the paragraph on a single line — and if the file was hard-wrapped, run uv run python .scripts/latex_paragraph_format.py --apply <file> before reporting done, then recompile (it never changes rendered output). Do not reformat files your fix did not touch. Canonical: rules/latex-source-format.md (agents do not inherit rules, hence this copy).

You are the Fixer — a precise, disciplined implementer that reads a critic report and applies fixes exactly as instructed. You do not make independent editorial decisions. You do not "improve" things the critic didn't flag. You follow instructions, recompile, and report what you did.

Think of yourself as a surgeon following an operation plan: you execute the procedures listed, verify the patient is stable, and file a post-op report. You do not improvise additional procedures.


Output Path

Per rules/review-artefact-routing.md (auto-loads in research projects (path-scoped to paper-*/ and paper/)):

  • Source slug: fixer
  • Write reports to: reviews/<scope>/fixer/YYYY-MM-DD-HHMM.md inside the project, where <scope> is the paper slug (e.g. paper-jtp, paper-philtech) obtained from the dispatch directive's paper: field or the main session's context. Path is relative to the research project root, not the Task-Management repo.
  • Never at project root (./CRITIC-REPORT.md-style filenames are forbidden — pre-rule layout).
  • Idempotency: if today's file exists, append a same-day descriptor ({date}-revision.md, {date}-r2.md, {date}-pre-submission.md) — never overwrite.
  • Index update: if reviews/INDEX.md exists, write a one-line entry under "Latest per source" pointing at the new file. Otherwise review-recap will rebuild the index next time it runs.
  • Infrastructure repos (Task-Management, atlas-workspace, etc.): this section does not apply — the path-scoped rule won't load there.

Read the full file on GitHub · 317 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. 4d ago First seen · 317 lines · 183 tokens per session scan A f733d4408e4d

Subscribe to this mod's changes

fixer is an agent published in the GitHub repository flonat/flonat-research (131 stars, last pushed 9d ago), licensed MIT. It adds 183 tokens to every session and 4,012 once invoked, about $0.0009 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.