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.
git clone --depth 1 https://github.com/aaronbassett/agent-foundryWrote 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.
[](https://agentmods.dev/commands/aaronbassett/agent-foundry/check-deps)<a href="https://agentmods.dev/commands/aaronbassett/agent-foundry/check-deps"><img src="https://agentmods.dev/badge/commands/aaronbassett/agent-foundry/check-deps.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.00810 |
| Opus 5 | $0.00028 | $0.00405 |
| Sonnet 5 | $0.00011 | $0.00162 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
devs:check-deps 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check project dependencies across all detected ecosystems by dispatching concurrent read-only devs:deps-maintenance agents.
Step 1 — Detect ecosystems, package managers, and workspace roots
Target directory: $ARGUMENTS if it is a path, else the current working directory. If $ARGUMENTS is typescript, rust, or python, detect everything but dispatch only that ecosystem.
Find manifests (cap depth at 4; exclude node_modules/, target/, .venv/, dist/, build/):
package.json→ typescriptCargo.toml→ rustpyproject.toml,requirements.txt→ python
Collapse to workspace roots — one dispatch per root, not per manifest. A package.json with a workspaces field, a directory with pnpm-workspace.yaml, a Cargo.toml with [workspace], or a pyproject.toml with [tool.uv.workspace] is a root; its member manifests are covered by it and get no separate dispatch.
Identify the package manager per root using the deps-core detection order: the packageManager field first, then the lockfile (pnpm-lock.yaml/package-lock.json/yarn.lock/bun.lock/bun.lockb; uv.lock/poetry.lock/Pipfile.lock/requirements.txt). Record it — the report headings use the detected manager, and a missing or duplicated lockfile is itself a finding to pass along.
If nothing is found, reply:
No supported dependency manifests found. Supported: TypeScript/JavaScript (package.json), Rust (Cargo.toml), Python (pyproject.toml / requirements.txt).
Step 2 — Dispatch one agent per ecosystem, concurrently
Each devs:deps-maintenance agent receives:
- Its ecosystem, detected package manager, and workspace root path(s).
- The mandate: "Read-only run — change nothing. Check for security vulnerabilities and outdated dependencies using the detected package manager's commands (prefer built-in auditors). If a needed tool is not installed, report the gap — do not install anything. Report findings grouped by severity; include the exact remediation commands a human would run, respecting the environment's install policy (sfw-wrapped, no npx). State every command you ran. If everything is clean, say so explicitly."
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.
- 8d ago First seen · 58 lines · 57 tokens per session scan A 9f53518d1253
devs:check-deps is a command published in the GitHub repository aaronbassett/agent-foundry (4 stars, last pushed 23d ago), licensed MIT. It adds 57 tokens to every session and 810 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 2026-08-31.
Other commands, from other repositories
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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.