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/godshiba/genesis/closenpx skills add godshiba/genesis --skill closegit clone --depth 1 https://github.com/godshiba/genesisWrote 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/godshiba/genesis/close)<a href="https://agentmods.dev/skills/godshiba/genesis/close"><img src="https://agentmods.dev/badge/skills/godshiba/genesis/close.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 | $0.00085 | $0.00917 |
| Opus 5 | $0.00043 | $0.00458 |
| Sonnet 5 | $0.00017 | $0.00183 |
| Haiku 4.5 | $0.00009 | $0.00092 |
Grade A, and why
close 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 3d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/genesis:close — End the Session Cleanly
The exit ritual. A session that ends without this destroys context the next
session will pay to rebuild. Requires docs/registry/ — if absent, just
summarize the work normally and suggest /genesis:init for next time.
Git is detected, not assumed. If git rev-parse --is-inside-work-tree
fails, this is not a repo: skip every commit, branch, and tree-settling step
below, and omit repo state from the handoff — record what changed and the next
step only. The handoff is file-based and works without git.
Steps
-
Gate audit first. Run the /genesis:gate-check checks. If G2 (validation) is red: do not close over it. Either fix it now or register the failure as an ISS-NNN and say explicitly that the tree is red and why. Never leave a broken tree silently.
-
Settle the tree (git repos only — skip entirely without a repo). Half-finished work is either completed, committed as a coherent WIP on a branch, or reverted — never left ambiguous. Ask the user which, if it is not obvious.
-
Append the SESSION_LOG.md entry (newest on top):
- What was completed, with file paths.
- Repo state: branch, last commit hash, and the check command result. Omit branch/commit when there is no git repo; still record the check result.
- The next concrete step — specific enough that a cold session can start from it without re-reading the whole repo ("implement X in file Y per ROADMAP phase N task M", not "continue").
- Anything in progress that should be reviewed first.
- Reference issues by ID only; bodies live in ISSUES.md.
-
Sync the roadmap. Check off completed ROADMAP.md tasks and update the status table if a phase boundary was crossed.
-
Clear the breadcrumb. If
docs/registry/.session-snapshot.mdexists (written automatically before a context compaction), delete it — a proper handoff supersedes the mechanical snapshot, and leaving it would mislead the next session into thinking work ended mid-task.
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.
- 3d ago First seen · 73 lines · 85 tokens per session scan A d9bf625eda52
close is a skill published in the GitHub repository godshiba/genesis (2 stars, last pushed 2mo ago), licensed MIT. It adds 85 tokens to every session and 917 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
to-plan
Capture the chat into .task/task/ .md with ## Description plus ## Plan (Goal/Touches/Logic) — the deepest one-task capture.
roadmap-to-workflow
Fan an approved .task/roadmap/ .md out to a dynamic Workflow — parallel planning, serialized implementation, dependency-ordered waves.
self-improve
Self-improve this skills repo — surface and (safely) apply quality improvements across four parallel read-only lenses (Clarity, Leanness, Coverage, Ergonomics). Sibling of /self-audit — audit fixes rule violations, improve raises quality where no rule is broken. Local meta-skill, independent of the /task: pipeline.
to-roadmap
Capture a multi-task initiative into .task/roadmap/ .md — a phase-grouped backlog of ready-to-pick-up items.
to-task
Capture the chat (or a roadmap item) into .task/task/ .md — ## Description only, no ## Plan.
self-audit
Self-audit this skills repo against CLAUDE.md invariants, the artifact contract, and README/CLAUDE.md/docs sync via three parallel read-only subagents. Local meta-skill — independent of the /task: pipeline.