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 itsribbZ/Godspeed --skill nyxgit clone --depth 1 https://github.com/itsribbZ/GodspeedWrote 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/itsribbz/godspeed/nyx)<a href="https://agentmods.dev/skills/itsribbz/godspeed/nyx"><img src="https://agentmods.dev/badge/skills/itsribbz/godspeed/nyx.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 | $0.00096 | $0.00901 |
| Opus 5 | $0.00048 | $0.00451 |
| Sonnet 5 | $0.00019 | $0.00180 |
| Haiku 4.5 | $0.00010 | $0.00090 |
Grade A, and why
nyx 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 6d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nyx — The Theater Auditor
Nyx was the primordial goddess of the night in Greek myth. In Homer, she audits the skill ecosystem for dead infrastructure while the user sleeps.
Role
Nyx is a sleep-time agent (L6). She runs on-demand or on a cron schedule and scans every skill SKILL.md in ~/.claude/skills/ for theater — version-tagged sections, NEW/UPGRADE labels, long spec blocks with zero file:line receipts, and "expected fire rate" hand-waving.
Nyx does NOT delete anything. She proposes PRUNE candidates and INVESTIGATE candidates via a dated report. the user reviews and greenlights per-item deletions through the standard v4.4 deletion proposal protocol.
What Nyx scans
For each ~/.claude/skills/<name>/SKILL.md:
- Read the file
- Run
Oracle.detect_theater(text)— same heuristic yesterday's manual godspeed audit used - Capture: size_bytes, line_count, theater_ratio, recommendation, suspect sections
- Also count
_learnings.mdentries (indicator of actual skill fires)
Output
A dated markdown report at Toke/automations/homer/sleep/nyx/reports/nyx_audit_YYYY-MM-DD.md:
- Summary header — skills audited, total bytes, PRUNE + INVESTIGATE counts
- Top theater ratios table — worst 25 skills by ratio, with learning entry counts
- PRUNE candidates section — deletion proposals ready for the user's greenlight
- Next steps — how to act on the report
When Nyx is useful
- After a build sprint — detect if new code landed without actual fire data
- Before a close-session — sanity-check what shipped vs what was real
- Weekly — track theater drift over time; healthy ecosystems shrink theater, sick ones grow it
- After a skill upgrade — verify the upgrade didn't add dead weight
Integration with Zeus + Oracle
- Zeus can dispatch Nyx as a maintenance task (rare — Nyx is mostly standalone)
- Oracle provides
detect_theater()— Nyx is a thin shell around Oracle's theater heuristic - Sleep CLI (
sleep_cli.py) dispatches Nyx viasleep run nyx
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.
- 6d ago First seen · 64 lines · 96 tokens per session scan A 3088ac4b427b
nyx is a skill published in the GitHub repository itsribbZ/Godspeed (1 stars, last pushed 2mo ago), licensed MIT. It adds 96 tokens to every session and 901 once invoked, about $0.0005 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
github-pr-review
Handles PR review comments and feedback resolution. Use when user wants to resolve PR comments, handle review feedback, fix review comments, address PR review, check review status, respond to reviewer, verify PR readiness, review PR comments, analyze review feedback, evaluate PR comments, assess review suggestions, or…
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
tech-lead
Channel operator (IRC handle @techlead) for the mARC agent team. Compiles chat demands into ready-to-execute work, records them on the GitHub Project board/Issues, and dispatches to specialists (@dev, @sre, @design, @sec, @rev, @research). Invoke with /tech-lead to turn discussion into tracked, delegated tasks.
init
Opt-in onboarding for the mARC agent team. Scaffolds a per-repo team binding so the team graduates from ephemeral session-memory to persistent, versioned config — without ever writing a file silently. Discovers the repo's org/repo/ project at runtime via gh, prefills {{ agentsdir }}/team.toml, and (optionally) a lean…
self-review
Surface the riskiest parts of the current diff so a reviewer knows where to look hardest — one inline pass on small diffs, parallel review lenses with adversarial synthesis on substantial ones. INVOKE PROACTIVELY whenever a change is finished and about to be handed off, reviewed, or shipped. It points attention …
review
Run a full code review on current changes or specified files. Runs ruff lint, review-code agent, and security scan in sequence.