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 skills add HigorAlves/orc --skill dependency-managementgit 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/skills/higoralves/orc/dependency-management)<a href="https://agentmods.dev/skills/higoralves/orc/dependency-management"><img src="https://agentmods.dev/badge/skills/higoralves/orc/dependency-management.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 | $0.00047 | $0.00864 |
| Opus 5 | $0.00023 | $0.00432 |
| Sonnet 5 | $0.00009 | $0.00173 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
dependency-management 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency Management
Doctrine for the three dependency verbs — audit (what's vulnerable), outdated (what's behind), upgrade (move safely). Ecosystem-specific commands and gotchas live in references:
| Ecosystem | Reference |
|---|---|
| npm / pnpm / yarn | <references/npm.md> |
| Python (pip / uv) | <references/python.md> |
| Go / Rust | <references/go-rust.md> |
Read the relevant reference before running any audit or upgrade command.
Audit
Prefer osv-scanner when installed (command -v osv-scanner) — it is ecosystem-agnostic, reads lockfiles directly, and covers polyglot repos in one pass:
osv-scanner scan --lockfile <lockfile> # or: osv-scanner scan -r .
Otherwise fall back to the native tool per ecosystem: npm audit / pip-audit / cargo audit / govulncheck (exact invocations + gotchas in references).
Severity-ranked reporting
Report findings ranked critical → high → moderate → low, never alphabetically or by package. For each: package, installed version, fixed version (if any), CVE/GHSA id, and whether the fix is a patch, minor, or major bump. Critical findings get the 🛑 danger callout. Distinguish:
- Fixable — a fixed version exists within the current major → candidate for the upgrade loop.
- Fixable via major — fix exists but requires a major bump → escalate (see below), never auto-apply.
- No fix yet — report it; suggest mitigations (overrides/constraints per references) only with user sign-off.
- Dev-only vs production — call out the dependency class; production trumps dev at equal severity.
Outdated
Survey with the ecosystem's outdated command. Report as a table: package, current, wanted (in-range), latest, and the bump class (patch/minor/major). Recommend a batch of safe bumps (patch + minor) — but the batch is still applied one bump at a time via the upgrade loop.
The upgrade loop
The iron discipline for applying any bump:
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 56 lines · 47 tokens per session scan A 3cb20349a4ea
dependency-management is a skill published in the GitHub repository HigorAlves/orc (6 stars, last pushed 12d ago), licensed MIT. It adds 47 tokens to every session and 864 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 skills, from other repositories
taiyi-ui-design
A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.
taiyi-evolve
A workflow skill that compares the implemented code with the frozen design after development and testing. It records architecture changes and proposes updates to DESIGN.md, the document describing the intended system structure.
taiyi-diagram-c4
A code-scanning tool that builds C4 architecture documents from a repository. It separates facts observed in the code from conclusions inferred about the design and uses Mermaid diagrams as the source format.
flow-next-resolve-pr
Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…