claudemd-code-analyst

claudemd-code-analyst is an agent for Claude Code from Sage-Bionetworks/agent-skills. It costs 39 tokens per session (722 once invoked), scanned A, original, Apache-2.0.

An agent that summarizes code and data-model changes made since a chosen commit for a CLAUDE.md file. CLAUDE.md is a project instruction file for Claude-based coding agents.

In plain words
What is it for?
Use it when evolving a CLAUDE.md file after code, build, linting, or data-model changes.
Why use it?
It identifies changes that may require updating those instructions without returning noisy raw diffs. It checks the default branch so the summary reflects shipped code rather than uncommitted work.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter; mentions CLAUDE.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the agent-skills plugin — 7 skills, 5 agents shipped together

Good fit Use it when evolving a CLAUDE.md file after code, build, linting, or data-model changes.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Sage-Bionetworks/agent-skills
Claude Code
/plugin install agent-skills

Made for: Claude Code.

Or install agent-skills, the plugin that ships this one along with the rest of its 7 skills, 5 agents.

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 claudemd-code-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/sage-bionetworks/agent-skills/claudemd-code-analyst.svg)](https://agentmods.dev/agents/sage-bionetworks/agent-skills/claudemd-code-analyst)
Your own site
<a href="https://agentmods.dev/agents/sage-bionetworks/agent-skills/claudemd-code-analyst"><img src="https://agentmods.dev/badge/agents/sage-bionetworks/agent-skills/claudemd-code-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 722 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 $0.00039 $0.00722
Opus 5 $0.00019 $0.00361
Sonnet 5 $0.00008 $0.00144
Haiku 4.5 $0.00004 $0.00072

Measured 7d ago against content hash 6857f0b314bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

claudemd-code-analyst 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 7d 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/claudemd-code-analyst.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md Code Analyst

You support the evolve-claudemd skill. Your job is to determine what changed in a code scope since a given commit and decide which changes should affect the scope's CLAUDE.md — without returning raw diffs to the parent.

Inputs (from the dispatching prompt)

  • scope_dir — the directory the CLAUDE.md governs (. for repo root)
  • since_commit — the commit that last touched that CLAUDE.md

Workflow

  1. Run the skill's gather script: bash "${CLAUDE_PLUGIN_ROOT}"/skills/evolve-claudemd/scripts/gather-code-changes.sh <scope_dir> <since_commit> It returns JSON buckets (added/deleted/modified, build_files, linter_configs, data_model_files) and a oneline commit list. Do NOT re-run raw git diff on the whole range — the buckets are your starting point.
  2. For the categorized files, read ONLY the handful that plausibly changed a documented convention, command, or data shape. Do not read everything.
  3. Verify against the default branch, not the working tree. CLAUDE.md documents shipped state. Confirm a finding actually exists on the repo's default branch with git ls-tree <default-branch> -- <path> (or git log <default-branch> -- <path>) before reporting it — the checkout may sit on an in-flight feature branch, and stale target//build//dist/ artifacts create false grep hits. Flag anything present only in the working tree as "not yet merged — do not canonize."
  4. Interpret, don't dump. For each finding, state the implication for CLAUDE.md.

What to surface

  • New/removed linter or formatter configs → conventions that should be REMOVED from CLAUDE.md (now tooling-enforced).
  • Build-file changes → new/changed commands, version bumps, new dependencies.
  • Data-model changes (flag prominently): new/modified/deleted schemas (JSON schema, protobuf, OpenAPI, DDL, TS types, Pydantic), codegen config changes, new/removed fields, changed enum values, new cross-boundary contracts.
  • New directories/modules → candidate new CLAUDE.md coverage.
  • Deleted files/dirs → stale references likely in CLAUDE.md.

Read the full file on GitHub · 51 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. 7d ago First seen · 51 lines · 39 tokens per session scan A 6857f0b314bb

Subscribe to this mod's changes

claudemd-code-analyst is an agent published in the GitHub repository Sage-Bionetworks/agent-skills (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 722 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 2026-08-31.

Related

Other agents, from other repositories

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens

dotnet-architecture-reviewer

Reviews a .NET codebase or repository and produces a structured architecture report — layering and dependency-rule violations, coupling, CQRS/handler hygiene, EF Core boundary leaks, testability, and concrete prioritized fixes. Use when the user wants an architecture review, a "second opinion" on structure, a PR-level…

StefanTheCode/dotnet-ai-toolkit · 102 tokens