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/codeprometheus/codex-buddy/releasenpx skills add CodePrometheus/codex-buddy --skill releasegit clone --depth 1 https://github.com/CodePrometheus/codex-buddyWhat 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 | $0.00083 | $0.01228 |
| Opus 5 | $0.00042 | $0.00614 |
| Sonnet 5 | $0.00017 | $0.00246 |
| Haiku 4.5 | $0.00008 | $0.00123 |
Grade A, and why
release 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 yesterday.
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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release codex-buddy
Publish the next codex-buddy version through the repository's existing cargo-dist and tray-app workflows. Treat the release as complete only after both workflows and all expected assets are verified.
Guardrails
- Use this skill from the beginning of every codex-buddy release, including release retries and verification-only requests.
- Work only in the
CodePrometheus/codex-buddycheckout. Verify the repository and readCLAUDE.mdbefore acting. - Treat an unqualified release request as authorization to commit the intended current changes, push
main, and push the selected version tag. Do not include unrelated changes. - Never rewrite published history, move an existing tag, delete a tag or release, or rerun or manually dispatch a failed workflow without explicit user approval.
- Report partial state truthfully. A pushed tag is not a completed release.
- Never print credentials or token values.
1. Inspect state
Run read-only checks first:
git remote -v
git status --short --branch
git diff
git fetch origin --tags --prune
git log --oneline --decorate -n 12
git tag --sort=-version:refname | head -n 10
gh auth status
gh release list --limit 10
Require:
- branch
main; - no unreviewed or unrelated local changes;
- local
mainnot behindorigin/main; - authenticated GitHub access;
- the target version absent locally and remotely.
For a small compatible fix, select the next patch after the highest stable vX.Y.Z tag. Ask before choosing a minor, major, or prerelease version when intent is ambiguous.
2. Prepare the release
Keep implementation and version commits separate when there are uncommitted product changes:
- Stage only the exact intended files and create a conventional
fix:,feat:,docs:, orchore:commit. - Update only
[workspace.package].versioninCargo.toml. - Do not add
Cargo.lock; this repository intentionally ignores it. - Commit the version change as
chore: bump version to X.Y.Z.
What ships with it
1 file 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.
- yesterday First seen · 137 lines · 83 tokens per session scan A cbe621688d07
release is a skill published in the GitHub repository CodePrometheus/codex-buddy (2 stars, last pushed 26d ago), licensed MIT. It adds 83 tokens to every session and 1,228 once invoked, about $0.0004 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
aptabase-analytics-report
Export and analyze Vibe Aptabase analytics for recent time windows or existing CSV exports, with emphasis on failure rates, affected users, app versions, and OS breakdowns. Use when Codex needs to: (1) export recent analytics with scripts/exportanalytics.py, (2) filter an export to the exact last N hours, (3) restrict…
claude-api
Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks for…
gmail
Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.
gui-onboarding-verification-skill
GUI desktop app only. Launch two parallel Oz cloud agents with computer use to download and install the latest stable Linux Warp build, capture screenshots while walking through first-time onboarding in both logged-out and logged-in states, then selectively fan out follow-up cloud agents for distinct onboarding…
create-skill
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
app-builder
Build and edit small, personal visual tools and artifacts — dashboards, trackers, calculators, data visualizations, charts, simple landing pages, and slide decks the user wants for THEMSELVES. This is the right skill whenever the user asks to "visualize this," "make a chart," or "build an artifact" for their own use…