codedna-reviewer

A code-review agent that checks whether source files include the required CodeDNA notes about their public functions, callers, rules, and editing history.

In plain words
What is it for?
Use it after files are written or edited, or when checking CodeDNA compliance. It reports passes, missing fields, broken caller references, and exports that do not exist.
Why use it?
It finds missing or inconsistent project documentation before the dependency map becomes unreliable. It reports problems without suggesting code changes.

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/larens94/codedna/codedna-reviewer
Clone the repo
git clone --depth 1 https://github.com/Larens94/codedna
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 359 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 $0.00050 $0.00359
Opus 5 $0.00025 $0.00179
Sonnet 5 $0.00010 $0.00072
Haiku 4.5 $0.00005 $0.00036

Measured yesterday against content hash 39a0063f3e21, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codedna-reviewer 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 yesterday.

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.

codedna-plugin/agents/codedna-reviewer.md · 36 lines

What it actually says

You are a CodeDNA compliance reviewer. Your job is to verify that source files follow the CodeDNA v0.9 annotation standard.

When invoked, you will receive a file path or a list of files to review.

For each file, check:

  1. Module docstring present — the file must start with a string literal (Python) or comment block (other languages) before any imports or code.

  2. Required fields present — the annotation must contain:

    • exports: with public API and return types
    • used_by: with caller file → caller function format
    • rules: with at least one hard constraint (or rules: none if truly no constraints)
    • agent: with at least one session entry in format model-id | YYYY-MM-DD | description
  3. used_by integrity — every file referenced in used_by: must exist in the project.

  4. No orphan exports — every symbol listed in exports: should appear in the actual code.

Report findings as:

PASS: path/to/file.py — all fields present, used_by valid
FAIL: path/to/file.py — missing: rules:, agent:
WARN: path/to/file.py — used_by references deleted_caller.py (not found)

Do not suggest code changes. Only report compliance status.

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. yesterday First seen · 36 lines · 50 tokens per session scan A 39a0063f3e21

Subscribe to this mod's changes

codedna-reviewer is an agent published in the GitHub repository Larens94/codedna (145 stars, last pushed 5d ago), licensed MIT. It adds 50 tokens to every session and 359 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

strategic-advisor

Activated for negotiation prep, deal analysis, interpersonal strategy, and high-stakes decision-making. Combines game theory with psychological awareness.

winstonkoh87/Athena-Public · 31 tokens

fsl-vacuity-reviewer

Use PROACTIVELY after adding or changing a .fsl spec under specs/ or examples/. Uses the working-tree native Rust CLI to detect hollowing, weak mutation kill-rate, vacuous properties, and weakened invariants. Read-only on specs; may run verifier commands.

ymm-oss/fsl · 64 tokens

agent_class

The Agent class is the core orchestrator in AgentForge. It loads configuration, renders prompts, invokes the LLM, and produces final outputs. Agents can be subclassed for custom logic.

DataBassGit/AgentForge · 0 tokens

surfaces

A Surface is a reusable, org-scoped, named capability/permission profile that gets merged into an agent's runtime environment. It bundles together everything that shapes what an agent may do and know for a given piece of work.

EpicStaff/EpicStaff · 0 tokens

Plan

Research and outline multi-step plans for zen analysis improvements.

Anselmoo/mcp-zen-of-languages · 13 tokens

gsc-content-optimizer

Finds content optimization targets across two zones, striking distance (positions 4-10) and page-two quick wins (positions 11-20). Use when asked for content ideas, quick wins, or optimization opportunities. Aussi déclenché en français par "quelles pages optimiser en priorité", "où je peux gagner vite", "mes pages en…

FlorianBruniaux/google-search-console-mcp · 110 tokens