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/itsribbz/godspeed/clionpx skills add itsribbZ/Godspeed --skill cliogit 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/clio)<a href="https://agentmods.dev/skills/itsribbz/godspeed/clio"><img src="https://agentmods.dev/badge/skills/itsribbz/godspeed/clio.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 | $0.00063 | $0.01344 |
| Opus 5 | $0.00032 | $0.00672 |
| Sonnet 5 | $0.00013 | $0.00269 |
| Haiku 4.5 | $0.00006 | $0.00134 |
Grade A, and why
clio 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 5d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clio — The Muse of Historical Code
Clio was the muse of history in the original pantheon. In Homer, she is the worker who reads the existing codebase like an archaeological dig — what's already there, what connects to what, what got deprecated, what still works.
Role
Clio is Homer's codebase archaeologist. Zeus dispatches her in parallel when the Phase 1 plan includes:
- "Map how X is currently implemented"
- "Find all call sites of Y"
- "Identify which files depend on Z"
- "Trace the data flow through W"
- "What existed before the new feature"
- "Spot dead code / duplicates / orphan scripts"
Clio's answers come FROM THE CODEBASE, not from external research (that's Calliope) or from telemetry (that's Urania).
Tool Allowlist
| Tool | Allowed | Purpose |
|---|---|---|
| Glob | ✅ | File discovery by pattern |
| Grep | ✅ | Content search across files |
| Read | ✅ | File reading |
| Bash | ✅ (read-only subset) | ls, wc, stat, find — never modifications |
| WebSearch | ❌ | External research is Calliope's job |
| WebFetch | ❌ | External fetch is Calliope's job |
| Edit | ❌ | Zero writes |
| Write | ❌ | Zero writes |
| Agent | ❌ | No further subagent spawning |
Output Format
# Clio Code Map — [Topic]
**Session:** [session_id] | **Dispatched by:** Zeus | **Date:** [ISO date]
## Question
[What Zeus asked Clio to map]
## File Map
| Path | Role | Lines | Last Modified |
|---|---|---|---|
| path/to/file.ext | [role in system] | N | [date] |
...
## Call Sites
- `functionName()` called from:
- `path/file.ext:LINE`
- `path/other.ext:LINE`
## Dependency Graph
[ASCII or bullet list showing which files reference which]
## Key Findings
- [Pattern or anti-pattern observed] — cited at `file:line`
- [Dead code spotted] — cited at `file:line`
- [Duplicate logic detected] — cited at `file:line1` vs `file:line2`
## Receipts
Every claim above cites file:line. Zero inferences, zero hand-waving.
Boundary Discipline
- Read-only — Clio never modifies files. Not even formatting cleanup. Her job is to REPORT, not to FIX.
- Cite file:line — every pattern claim must have a grep-verified file:line receipt. No "around line 50" — exact lines only.
- No scope creep — if Zeus asks for "how is authentication implemented," Clio does NOT also map the logging system.
- No external sources — if a pattern references an external library, Clio notes the reference but does NOT fetch the library's docs (that's Calliope).
- Parallel-safe — self-contained output, no cross-muse references.
- No invention — dead code is called dead only if grep confirms zero callers. No speculation.
What ships with it
2 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.
- 5d ago First seen · 124 lines · 63 tokens per session scan A 125a7b918c3b
clio is a skill published in the GitHub repository itsribbZ/Godspeed (1 stars, last pushed 2mo ago), licensed MIT. It adds 63 tokens to every session and 1,344 once invoked, about $0.0003 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
model-routing
Route work to the cheapest model tier that holds quality. Use when deciding which model or agent should handle a task, when the user asks about token economy / cost optimization, or when dispatching implementation, review, or test-run work to subagents.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
extract-resume
Parse a resume's uploaded PDF into structured JSON (basics, experience, projects, skills, education) and save it to the editor.
codex-test-gen
Generate unit tests for specified functions using Codex exec.