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 nphausg/ai-agent-skills --skill fridaygit clone --depth 1 https://github.com/nphausg/ai-agent-skillsWrote 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/nphausg/ai-agent-skills/friday)<a href="https://agentmods.dev/skills/nphausg/ai-agent-skills/friday"><img src="https://agentmods.dev/badge/skills/nphausg/ai-agent-skills/friday/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/nphausg/ai-agent-skills/friday"><img src="https://agentmods.dev/badge/skills/nphausg/ai-agent-skills/friday.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00085 | $0.00789 |
| Opus 5 | $0.00043 | $0.00394 |
| Sonnet 5 | $0.00017 | $0.00158 |
| Haiku 4.5 | $0.00009 | $0.00079 |
Grade A, and why
friday 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 9d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
friday — Plan / Codex / Review / Evidence-Test Orchestration Loop
friday implements the user's tasks one at a time through a fixed per-task pipeline. This session coordinates only — it never writes feature code; it delegates planning, implementation, review, and testing, gates on approval, and does git. Every subagent and Codex run is stateless, so each dispatch must carry full context (task, paths, repo, conventions, constraints, deliverable).
Read references/pipeline.md before running — it holds the full per-step
procedure, coding principles, model selection, completion tracking, and the
discipline gates.
Pipeline (per task)
- Brainstorm —
superpowers:brainstormingwith the user (skip in execute mode). - Plan — Fable subagent writes a timestamped
plan_<timestamp>.md(skip in execute mode). - Approve — explicit user approval of the plan (skip in execute mode).
- Implement —
codex execruns the plan in the background (≤30 min); post progress. - Review — a parallel team of Codex adversarial reviewers, one per lens (correctness / security / performance / approach); any finding blocks -> rework to step 3 and re-review the whole team until every lens approves.
- Smoke test — Opus subagent PROVES it works with captured evidence; root-cause any failure.
- Ship — commit only (no push), then the next task.
Modes
- Full loop (default) — run the whole pipeline including plan + approval.
- Execute mode — the user supplies a ready plan file; treat it as approved, skip steps 0–2, start at Implement piping that file. Never edit the user's file (pipe an augmented scratchpad copy if it isn't self-contained). Multiple tasks run sequentially, each with its own review -> smoke -> ship.
Completion bar
First action of every run: create a TodoWrite checklist whose items ARE the
run's match criteria, so the loop self-continues instead of stopping early. A
task is done only when (a) every review lens approves, (b) the evidenced smoke
test PASSes, and (c) it is committed locally (no push). Fold user acceptance
criteria in verbatim.
What ships with it
4 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.
- 9d ago First seen · 63 lines · 85 tokens per session scan A 2f6b9869d656
friday is a skill published in the GitHub repository nphausg/ai-agent-skills (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 85 tokens to every session and 789 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
commit
Create well-formatted commits with conventional commit messages and emoji.
git-notes
Use when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messages post-hoc - provides git notes commands and patterns for attaching non-invasive metadata to Git objects.
commit
Write clear commit messages in conventional commits format. Use when the user is done with changes and wants to commit, says 'commit this', asks for a commit message, or has staged changes ready to go.
git-commit-push
Enforces Git commit standards and conventions when committing and pushing code in Agent Mode. This rule is crucial for keeping track of changes made by agents, and should run whenever the user expresses they want to commit or push code changes made by the agent. This rule should be followed when: 1. the user wants to…
create-hook
Create and configure git hooks with intelligent project analysis, suggestions, and automated testing.
git-commit
Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive…