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 skills/thienan230427/codex-github-skill-manager/manage-github-skillsnpx skills add thienan230427/codex-github-skill-manager --skill manage-github-skillsgit clone --depth 1 https://github.com/thienan230427/codex-github-skill-managerWrote 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/thienan230427/codex-github-skill-manager/manage-github-skills)<a href="https://agentmods.dev/skills/thienan230427/codex-github-skill-manager/manage-github-skills"><img src="https://agentmods.dev/badge/skills/thienan230427/codex-github-skill-manager/manage-github-skills.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 | $0.00133 | $0.01585 |
| Opus 5 | $0.00067 | $0.00792 |
| Sonnet 5 | $0.00027 | $0.00317 |
| Haiku 4.5 | $0.00013 | $0.00159 |
Grade A, and why
manage-github-skills scanned grade A with 1 finding 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 4d 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.
Enumerates other installed skillslowAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
5. **Dry run**: `gh skill update --dir <managed-root> --dry-run` before any update mutation. The legacy `~/.codex/skills` root is discovery/migration-only and is never an update target. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage GitHub Skills
Manage external GitHub-backed Codex Agent Skills with deterministic local discovery and GitHub CLI provenance.
Startup behavior
This plugin bundles a trusted-once SessionStart hook. After the user reviews and trusts the hook in Codex, each new Codex session performs a bounded bootstrap:
- Discover
$HOME/.agents/skills, current-project.agents/skillsroots, and an existing$HOME/.codex/skillslegacy root. - Read GitHub CLI metadata injected into installed
SKILL.mdfiles and compatible.skill-lock.jsonentries. - Trust a legacy source only when the user previously registered that exact root/folder mapping. Git remotes and labelled repository URLs are candidates for review, never automatic provenance.
- Clone each missing confirmed user/legacy
OWNER/REPOonly once into$HOME/.agents/.codex-github-skill-manager/repos/OWNER/REPO. Project sources are discovery-only at startup. - Return a short discovery summary to Codex so later update requests route to this skill.
The startup hook does not update installed skills, overwrite local files, auto-clone project-controlled sources, or execute scripts from cloned repositories.
Unknown legacy source fallback
If discovery reports source-unknown, the previous installer did not preserve enough provenance to identify the GitHub repository safely. Do not search/guess solely from the skill name. Ask for the repository URL once, then register it:
python scripts/skill_manager.py register --skill SKILL_NAME --repo OWNER/REPO --json
An HTTPS GitHub repository URL is also accepted. If the same name exists in more than one scope, add --root PATH_TO_EXACT_SKILL_ROOT. Add --skill-path path/to/SKILL.md when known so later migration is exact. After registration, run bootstrap or sync; future startup/resume discovery will reuse the scope-bound mapping automatically.
Default update workflow
When the user asks to update/sync GitHub skills, use the bundled manager from this skill directory:
What ships with it
5 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.
- 4d ago First seen · 138 lines · 133 tokens per session scan A 180e92895222
manage-github-skills is a skill published in the GitHub repository thienan230427/codex-github-skill-manager (30 stars, last pushed 24d ago), licensed MIT. It adds 133 tokens to every session and 1,585 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…