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.
npx agentmods add commands/larens94/codedna/manifestgit clone --depth 1 https://github.com/Larens94/codednaWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00020 | $0.00386 |
| Opus 5 | $0.00010 | $0.00193 |
| Sonnet 5 | $0.00004 | $0.00077 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
manifest 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 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.
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.
What it actually says
/codedna:manifest
Build a complete architectural map of the project by reading only the module docstrings (first 10-15 lines) of every source file. Do NOT read full file contents.
-
Scan all source files (exclude
venv/,node_modules/,.git/,__pycache__/,dist/,build/). -
For each file, extract only the module-level annotation fields:
exports:— public APIused_by:— reverse dependency graphrules:— hard constraintsagent:— last session entry
-
Output a structured map grouped by directory:
CodeDNA Architectural Map
=========================
api/routes.py
exports: revenue_route(req) -> Response
used_by: workers/report.py → generate
rules: all routes require auth middleware before handler
agent: claude-sonnet-4-6 | 2026-03-20 | added rate limiting
utils/format.py
exports: format_currency(n) -> str | format_date(d) -> str
used_by: api/routes.py → revenue_route | views/dashboard.py → render
rules: format_currency uses locale from request context, never hardcode
[unannotated]
migrations/001.py
new_feature.py
- After the map, output a one-line summary:
<N> files mapped | <N> unannotated | <N> dependency edges
This command is designed to replace 10-20 individual file reads at the start of a session. Use it as the first step before any multi-file task.
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.
- 2d ago First seen · 45 lines · 20 tokens per session scan A 2cf6320ae0c9
manifest is a command published in the GitHub repository Larens94/codedna (145 stars, last pushed 6d ago), licensed MIT. It adds 20 tokens to every session and 386 once invoked, about $0.0001 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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.