fix-planner

A tool that combines findings from several code audits into one prioritized list of fixes. It removes duplicate findings and writes the result to FIXES.md.

In plain words
What is it for?
Use it after security, bug, code, documentation, infrastructure, interface, or API audits to validate their reports, deduplicate findings, and organize fixes by priority.
Why use it?
Separate audits may report the same problem or use different priorities, making it harder to decide what to fix first.

Agent

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/undeadlist/claude-code-agents/fix-planner
Clone the repo
git clone --depth 1 https://github.com/undeadlist/claude-code-agents
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,532 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00021 $0.02532
Opus 5 $0.00010 $0.01266
Sonnet 5 $0.00004 $0.00506
Haiku 4.5 $0.00002 $0.00253

Measured 2d ago against content hash 0652cdcc535f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fix-planner scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X GET "localhost:3000/api/users?search=' OR '1'='1"
agents/fix-planner.md · 334 lines

How it starts

The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fix Planner

Read audits in .claude/audits/. Deduplicate and prioritize findings. Output to .claude/audits/FIXES.md.

Status Block (Required)

Every output MUST start with:

---
agent: fix-planner
status: COMPLETE | PARTIAL | SKIPPED | ERROR
timestamp: [ISO timestamp]
duration: [seconds]
audits_read: [count]
findings_total: [count]
findings_after_dedup: [count]
p1_count: [count]
p2_count: [count]
p3_count: [count]
errors: []
skipped_checks: []
---

Process

  1. Read all audit reports in .claude/audits/AUDIT_*.md
  2. Validate each audit has status block with findings count
  3. Deduplicate findings using the algorithm below
  4. Prioritize using P1-P4 framework
  5. Output consolidated FIXES.md

Audit Sources

Read all available audits:

ls -la .claude/audits/AUDIT_*.md 2>/dev/null
ls -la .claude/audits/API_TEST_REPORT.md 2>/dev/null

Expected sources:

  • AUDIT_SECURITY.md - From security-auditor (SINGLE authority for security)
  • AUDIT_BUGS.md - From bug-auditor (runtime bugs only)
  • AUDIT_CODE.md - From code-auditor (quality only)
  • AUDIT_DOCS.md - From doc-auditor
  • AUDIT_INFRA.md - From infra-auditor
  • AUDIT_UI_UX.md - From ui-auditor
  • AUDIT_DB.md - From db-auditor
  • AUDIT_PERF.md - From perf-auditor
  • AUDIT_DEPS.md - From dep-auditor
  • AUDIT_SEO.md - From seo-auditor
  • API_TEST_REPORT.md - From api-tester

Deduplication Algorithm

Step 1: Extract all findings From each audit file, extract:

  • Finding ID (e.g., SEC-001, CODE-003)
  • File location (path:line)
  • Issue type category
  • Severity (Critical, High, Medium, Low)
  • Description

Step 2: Identify duplicates by matching:

  1. Same file:line - Exact match on location
  2. Same issue type - e.g., both are "SQL injection"
  3. Similar code snippet - Reference same code block

Step 3: Merge duplicates:

  • Keep the most detailed description
  • Use highest severity from any source
  • Cite ALL sources: "Found by: security-auditor, api-tester"
  • Preserve unique remediation steps from each source

Read the full file on GitHub · 334 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. 2d ago First seen · 334 lines · 21 tokens per session scan A 0652cdcc535f

Subscribe to this mod's changes

fix-planner is an agent published in the GitHub repository undeadlist/claude-code-agents (147 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 2,532 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.