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/higoralves/orc/depsgit clone --depth 1 https://github.com/HigorAlves/orcWrote 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/higoralves/orc/deps)<a href="https://agentmods.dev/commands/higoralves/orc/deps"><img src="https://agentmods.dev/badge/commands/higoralves/orc/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 | $0.00038 | $0.01757 |
| Opus 5 | $0.00019 | $0.00879 |
| Sonnet 5 | $0.00008 | $0.00351 |
| Haiku 4.5 | $0.00004 | $0.00176 |
Grade A, and why
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 5d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orc:deps
Dependency hygiene for the current repo: what's vulnerable, what's behind, and how to move — safely. Doctrine lives in orc:dependency-management (invoke it first; its references/ carry the exact per-ecosystem commands).
Arguments
audit(default) — scan for vulnerabilities, report severity-ranked, offer the upgrade loop for fixables.outdated— survey what's behind; recommend a safe batch.upgrade [pkg | --all-safe]— run the one-bump-per-commit loop for a named package, or for every safe (patch/minor, in-range) bump.--prod-only— audit/survey production dependencies only.--repos a,b/--repo a/--all-repos/--this-repo— workspace-mode targeting. Seeorc:workspace-mode.
Workflow
Phase 0 — Detect context
!orc-workspace-detect --banner
Context is injected above (ORC_* vars are exported for any Bash you run — do not re-run detection). In workspace mode, resolve target repos from flags or AskUserQuestion — iron rule: no silent broadcast. Each target repo gets its own report/loop.
Phase 1 — Resolve verb + ecosystems
$verb is the first argument (audit when empty). Invoke orc:dependency-management and detect ecosystems by lockfile/manifest presence (package-lock.json/pnpm-lock.yaml/yarn.lock, requirements.txt/uv.lock/poetry.lock, go.mod, Cargo.lock). Check command -v osv-scanner — prefer it when installed; else the native scanner per the matching references/ file. A repo can hit multiple ecosystems — run all that match.
Phase 2 — audit (default)
- Run the scanner(s) per
orc:dependency-management. Uncommitted lockfile changes → surface first (git status), don't audit a dirty tree silently. - Render the severity-ranked report (critical → high → moderate → low): package, installed, fixed-in, advisory id, bump class (patch/minor/major), prod vs dev. When criticals exist, lead with:
> **🛑 Critical vulnerabilities**
>
> <N> critical finding(s): <pkg@version — advisory id, one per line>. Fix or mitigate before shipping anything from this branch.
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.
- 5d ago First seen · 132 lines · 38 tokens per session scan A 5240c75d571c
deps is a command published in the GitHub repository HigorAlves/orc (6 stars, last pushed 9d ago), licensed MIT. It adds 38 tokens to every session and 1,757 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.
Other commands, from other repositories
land
Cadence-tick autonomous PR babysitter (CI-fix, resolve, converge, merge, close, release).
sync
Manually trigger plan-sync to update downstream task specs after implementation drift.
setup
Set up Postman MCP Server. Authenticate via OAuth or API key, verify connection, select workspace.
uninstall
Remove flow-next files from project.
test
Run Postman collection tests, analyze results, diagnose failures, and suggest fixes.
refine-title
深度分析 Issue 或 PR 内容，并将其标题重构为 Conventional Commits 格式.