Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/vanducng/skillsnpx agentmods add skills/vanducng/skills/skill-managementWrote 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/vanducng/skills/skill-management)<a href="https://agentmods.dev/skills/vanducng/skills/skill-management"><img src="https://agentmods.dev/badge/skills/vanducng/skills/skill-management/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vanducng/skills/skill-management"><img src="https://agentmods.dev/badge/skills/vanducng/skills/skill-management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 56 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 166 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00117 | $0.01765 |
| Opus 5 | $0.00059 | $0.00882 |
| Sonnet 5 | $0.00023 | $0.00353 |
| Haiku 4.5 | $0.00012 | $0.00177 |
Grade A, and why
skill-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 7d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skill-management
One entry point for everything skill-lifecycle in vanducng/skills:
authoring (delegates to skill-creator), vendoring (delegates to the
vd CLI), and releases (driven by conventional commits + release-please).
Use canonical skill IDs in docs and handoffs: write
vd:cook plans/path/ without a leading invocation prefix. The user adds the
runtime prefix when invoking it: slash in Claude Code, dollar in Codex.
Pick the flag that matches user intent. Never re-implement what
skill-creator or vd already does - orchestrate them.
Modes
| Flag | What it does | Underlying tool |
|---|---|---|
--create [name] |
Author a new skill (eval-driven loop) | skill-creator Skill |
--list |
Show tracked skills from skills.toml |
vd list |
--add <src> |
Track a new upstream skill | vd add |
--sync |
Vendor tracked skills into skills/ |
vd sync |
--update [name] |
Bump tracked skills to upstream HEAD | vd update |
--remove <name> |
Drop a tracked skill | vd remove |
--diff <name> |
Show drift vs cached upstream | vd diff |
--doctor |
Report drift between lock + disk | vd doctor |
--validate |
Lint frontmatter of every local skill | bash scripts/validate.sh |
--release [bump] |
Use the skill-catalog release workflow | release-please (CI) |
If no flag is given, ask the user which lifecycle stage they want (authoring / vendoring / releasing) before doing anything.
Repo conventions (must respect)
- Local skills live in
skills/<name>/SKILL.md. Names: kebab-case. - Frontmatter required keys:
name,description,license. ThenameMUST equal the directory basename, anddescriptionmust be ≤ 1024 characters -scripts/validate.shenforces both. vdis the standalone CLI atvanducng/vd-cli(brew install vanducng/tap/vdorgo install github.com/vanducng/vd-cli/v2/cmd/vd@latest). This repo no longer contains its source.- Plugin manifest version (
.claude-plugin/marketplace.json,.claude-plugin/plugin.json) is for the skill catalog and must matchversion.txtplus[targets.claude.bundle].versioninskills.toml. ThevdCLI versions independently in its own repo.
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.
- 7d ago First seen · 172 lines · 117 tokens per session scan A 9480c7bbb851
skill-management is a skill published in the GitHub repository vanducng/skills (7 stars, last pushed today), licensed MIT. It adds 117 tokens to every session and 1,765 once invoked, about $0.0006 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 2026-09-04.
Other skills, from other repositories
changelog-gen
A changelog generator that turns Git history into a version-by-version record of project changes. A changelog is a readable summary of new features, fixes, breaking changes, documentation, and other updates.
changelog-rules
Shared changelog conventions and formatting rules referenced by /create-changelog and /update-changelog. Not typically invoked directly.
aiwg-pr
AIWG-specific pull request delivery workflow for AIWG product/workspace changes; not the generic repository PR process.
artifact-metadata
Manage artifact metadata, versioning, ownership, and review history across the SDLC lifecycle.
git-mirror-audit
Verify configured secondary git mirrors are present and not drifting from the primary remote/default branch.
update-changelog
Update the Unreleased section of CHANGELOG.md based on current changes. No-op if CHANGELOG.md does not exist. Use when the user asks to "update changelog", "add to changelog", "update the changelog", "changelog entry", "add changelog entry", or "log this change".