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 hespergit 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/hesper)<a href="https://agentmods.dev/skills/itsribbz/godspeed/hesper"><img src="https://agentmods.dev/badge/skills/itsribbz/godspeed/hesper.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 | $0.00092 | $0.01058 |
| Opus 5 | $0.00046 | $0.00529 |
| Sonnet 5 | $0.00018 | $0.00212 |
| Haiku 4.5 | $0.00009 | $0.00106 |
Grade A, and why
hesper 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hesper — The Learning Distiller
Hesper was the evening star in Greek myth — the calm, steady light at day's end. In Homer, she runs at day's end too: mining everything Toke learned today, distilling it into a best-practices KB before the next session begins.
Role
Hesper is a sleep-time agent (L6). She mines all learning sources across Toke, ranks entries by composite score, and produces a dated best-practices markdown report.
This absorbs the original Kiln blueprint mission. Kiln was going to be a standalone distillation engine; Hesper is the same thing as a sleep-time agent inside Homer.
Sources Mined
| Source | Path | What it contributes |
|---|---|---|
| Per-skill learnings | ~/.claude/skills/*/_learnings.md |
Skill-local patterns, calibration echoes, escalation events |
| Shared learnings | ~/.claude/shared/_shared_learnings.md |
Cross-skill promoted SL-NNN rules |
| Toke research | Toke/research/*.md |
T1-T3 source-backed research findings |
| Mnemos archival | Toke/automations/homer/mnemos/archival/*.md |
Previously high-value memory entries |
Composite Score Formula
score = roi_score × confidence_rank × max(1, confirmed_count)
where confidence_rank = {HIGH: 3, MEDIUM: 2, LOW: 1}
Entries are extracted from structured <!-- meta: {...} --> comments if present (the v2.0 structured learning format from _shared_protocols.md), or default to (1, "LOW", 1) for free-form entries.
Top-N (default 20) are written to the best-practices report, newest + highest-score first.
Output
Toke/automations/homer/sleep/hesper/best_practices/best_practices_YYYY-MM-DD.md
Contains:
- Summary header — sources mined, top-N size
- Top-N patterns — each with title, skill, date, score breakdown, SL-IDs referenced, source path, body excerpt
- Usage notes — how to feed the top-5 into Zeus Phase 1 plans as injected context
When Hesper is useful
- Weekly — distill what the ecosystem learned over the past 7 days
- After a big sprint — capture what the sprint taught that's worth promoting
- Before a close-session — surface the session's highest-yield insights for the Rosetta Stone candidates
- Before Zeus dispatches — feed top-5 into the plan prompt as prior-art context
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 · 78 lines · 92 tokens per session scan A eb02eba9118b
hesper is a skill published in the GitHub repository itsribbZ/Godspeed (1 stars, last pushed 2mo ago), licensed MIT. It adds 92 tokens to every session and 1,058 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
cco-patterns
Share learned file patterns across a team — export an anonymized digest of what's usually waste/useful/co-edited, and import a teammate's so a fresh clone benefits day one.
dream
Prunes and consolidates the project's auto-memory to keep it minimal — deletes stale, wrong, or redundant memories, merges overlapping ones into existing files, and trims the index. Strong bias against growth: never creates new memory files and never stores new facts. Verifies staleness against the current codebase…
team-memory-protocol
A shared-memory process for teams of coding agents working on the same build. It stores project knowledge, shared context, and task progress in separate files or repositories.
magic-compact
Compact this Claude Code session.
knowledge-wiki
A tool that turns useful lessons from coding sessions into general articles for a team wiki. A wiki is a collection of linked reference pages, and this one can be kept locally or shared through a Git repository.
memem-mine
Opt in to memem's event-triggered mining. New sessions are mined automatically via the Stop hook.