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 RockyHong/super-bootstrap --skill session-closegit clone --depth 1 https://github.com/RockyHong/super-bootstrapWrote 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/rockyhong/super-bootstrap/session-close)<a href="https://agentmods.dev/skills/rockyhong/super-bootstrap/session-close"><img src="https://agentmods.dev/badge/skills/rockyhong/super-bootstrap/session-close/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/rockyhong/super-bootstrap/session-close"><img src="https://agentmods.dev/badge/skills/rockyhong/super-bootstrap/session-close.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 | $0.00181 | $0.02302 |
| Opus 5.5 | $0.00072 | $0.00921 |
| Sonnet 5.5 | $0.00036 | $0.00460 |
| Haiku 4.5 | $0.00018 | $0.00230 |
Grade A, and why
session-close scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Close — Session-Boundary Gate
Two terminal shapes
| Detected state | Shape |
|---|---|
| Goal delivered whole, nothing in-motion | done-close — closeout moves + own carry cleared |
| In-motion remainder (mid-work break, topic switch, context heavy) | park-close — closeout moves + Progress block on the card + carry landed in the ledger |
Step 1 routes by fulfillment; on ambiguity the user's framing wins — only they know a done session from a pause.
Ledger convention
This section is the convention's SSOT; /super-bootstrap:session-continue reads it from here.
- Path —
SESSION-STATE/<label>-<id>.mdat the repo root, one file per session.<label>= short anchor-derived slug (the card ID when card-anchored);<id>= first 8 chars of$CLAUDE_CODE_SESSION_ID(absent →date +%H%M%S). - Slots — Anchor / Read first / State / Next step / Watch-outs.
- Park = whole-file rewrite of the own file (git holds history). Done = delete the own file. A file present = that session's carry is in flight.
- Conflict (merge markers from a cross-branch carry) → keep either side or regenerate from current state; never hand-merge.
Protocol
The gateway runs this inline — it inspects the live session's work and tree, dispatches no subagent, pins no model.
Two passes: detect every open closeout move (steps 1–3) — read-only, nothing written — then drive them to done in one confirm-pick (step 4).
1. Detect — fulfillment → shape
Is this session's goal delivered whole, with nothing left in motion? Whole → done-close. An in-motion remainder — a live next-step, a half-built change, a break arriving mid-work → park-close. An undelivered goal the user expects finished this session is neither — carry it to step 4's surface, not the move-pick.
2. Detect — tree + commit
Inspect for uncommitted session work, untracked files, stray artifacts — this session's changes only. Session changes → a commit move, run through /super-bootstrap:commit (Skill tool) — the door owns staging, doc-sync, and the message; never a raw git commit. Commits ahead of upstream, or a push the commit will create → a push move, answered in the pick.
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 Changed a6fc6066e93e
- 18d ago Changed · +6 lines · +19 tokens per session 5ebb919afc7c
- 22d ago First seen · 85 lines · 162 tokens per session scan A a13c97e2a85a
session-close is a skill published in the GitHub repository RockyHong/super-bootstrap (3 stars, last pushed 9d ago), licensed MIT. It adds 181 tokens to every session and 2,302 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-09-28.
Other skills, from other repositories
alive-bundle
Create, manage, and graduate bundles -- the unit of focused work within a walnut.
plan-to-tasks
Transform a plancreation planv{N}.md into a structured tasks.yaml + per-WP workpackages/.yaml using parallel Sonnet sub-agents. Use after plan-creation finishes when you need execution-friendly task structure.
session-handoff
Create consistent session handoff documents for context transfer between sessions. Use when closing a session, reaching 75% token consumption, or when user requests handoff. Ensures proper YAML headers for metrics collection, LF line endings, and complete documentation of progress, decisions, and next steps.
maintaining-session-continuity
Judgment for using cc-reload — carrying a session's working thread across a context reset via .reload/session.md: snapshot, arm, rehydrate after /clear, /compact, or auto-compaction. Use when saving state before a reset, handing off mid-task, holding working state as context fills, or working with /snapshot, /reload…
brain-log
Show brain sync and evolution history.
memory-graveyard
Audit which entries in your project's MEMORY.md Claude actually reads. Use when the user wants to find dead memory entries, broken pointers in MEMORY.md, orphan memory files, or surface entries that fall below the system-prompt truncation cutoff. Triggers on "audit MEMORY.md", "dead memory entries", "broken memory…