agentmods.dev

codeatlas-platform: Agent for Claude Code

.claude/agents/codeatlas-implementer.md

codeatlas-implementer is an agent for Claude Code from giauphan/codeatlas-platform. It costs 25 tokens per session (348 once invoked), scanned A, original, MIT.

A coding-agent guide for implementing CodeAtlas features, bug fixes, and small refactors while keeping the existing software structure intact. It emphasizes SQLite, focused tests, and checks before changes are finished.

In plain words
What is it for?
Use it to trace CodeAtlas code, make a narrowly scoped change, update tests, and run type, build, and test checks for the main project and dashboard.
Why use it?
It reduces the risk of breaking unrelated work, putting code in the wrong layer, or introducing unsafe database queries. It also gives the agent a defined set of checks for confirming a change works.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is giauphan/codeatlas-platform's own configuration. It tells Claude Code how to work on codeatlas-platform 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 codeatlas-platform configures →

not rated 12repo 2d ago A scan 25 tokens original MIT
View source ↗ giauphan/codeatlas-platform
Reuse

Borrowing it

Nothing to install: this file belongs to giauphan/codeatlas-platform. 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/giauphan/codeatlas-platform/main/.claude/agents/codeatlas-implementer.md
Clone the repo
git clone --depth 1 https://github.com/giauphan/codeatlas-platform

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 codeatlas-implementer

README.md
[![agentmods](https://agentmods.dev/badge/agents/giauphan/codeatlas-platform/codeatlas-implementer/github.svg)](https://agentmods.dev/agents/giauphan/codeatlas-platform/codeatlas-implementer)
Your own site
<a href="https://agentmods.dev/agents/giauphan/codeatlas-platform/codeatlas-implementer"><img src="https://agentmods.dev/badge/agents/giauphan/codeatlas-platform/codeatlas-implementer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for codeatlas-implementer

Your own site · 80×15
<a href="https://agentmods.dev/agents/giauphan/codeatlas-platform/codeatlas-implementer"><img src="https://agentmods.dev/badge/agents/giauphan/codeatlas-platform/codeatlas-implementer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 348 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 $0.00025 $0.00348
Opus 5.5 $0.00010 $0.00139
Sonnet 5.5 $0.00005 $0.00070
Haiku 4.5 $0.00003 $0.00035

Measured 2mo ago against content hash cd2d2f876afa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codeatlas-implementer 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 2mo 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/codeatlas-implementer.md · 35 lines

What it actually says

CodeAtlas Implementer

Use for feature work, bug fixes, and focused refactors.

Workflow

  1. Read root CLAUDE.md and .claude/CLAUDE.md.
  2. Run git status --short; preserve unrelated changes.
  3. Trace the feature with CodeAtlas MCP tools when available.
  4. Read affected implementation and tests before editing.
  5. Keep presentation, service, repository, and database responsibilities in their existing layers.
  6. Treat SQLite + sqlite-vec as default. Preserve optional adapter compatibility only when shared contracts change.
  7. Implement smallest correct change.
  8. Add or update tests for changed behavior.
  9. Run root gates: pnpm run typecheck, pnpm run build, pnpm test.
  10. Run dashboard gates: cd dashboard && pnpm run typecheck, pnpm run build, pnpm test.
  11. Review git diff --check and final diff.
  12. Call sync_system_memory after code changes.
  13. Review git diff --check and final diff.
  14. Call sync_system_memory after code changes.

Rules

  • Do not use any for external data; use unknown and narrow it.
  • Bind SQL values. Never interpolate user input into SQL.
  • Do not add credentials, generated databases, build output, or personal data.
  • Do not reset, clean, stash, commit, or push automatically.
  • Do not overwrite unrelated user changes.
  • Report skipped or failed verification explicitly.
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. 2mo ago First seen · 35 lines · 25 tokens per session scan A cd2d2f876afa

Subscribe to this mod's changes

codeatlas-implementer is an agent published in the GitHub repository giauphan/codeatlas-platform (12 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 348 once invoked, about $0.0001 per session on Opus 5.5. 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.

agentic-aiaiastcode-analysiscodebase-intelligencedeveloper-tools
Related

codeatlas-implementer compared with agents from other repositories

codeatlas-implementer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
codeatlas-implementergiauphan/codeatlas-platformAgent122d agoMITA25Claude Code
cisoch015/code-pentesterAgent419d agoMITA34Claude Code
dependencylibraries-related-files-searchFI-Mihej/codebase-agent-mcpAgent31mo agoApache-2.0A157Claude Code
dependencylibraries-analysisFI-Mihej/codebase-agent-mcpAgent31mo agoApache-2.0A127Claude Code
dependencylibraries-list-librariesFI-Mihej/codebase-agent-mcpAgent31mo agoApache-2.0A44Claude Code
analyzerfeiskyer/claude-code-settingsAgent1.7kyesterdayMITA29Claude Code
nw-ux-designernWave-ai/nWaveAgent631yesterdayMITA31Claude Code