Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ManceRayder42/jarvis-os/plugin install jarvis-osWrote 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/mancerayder42/jarvis-os/done)<a href="https://agentmods.dev/skills/mancerayder42/jarvis-os/done"><img src="https://agentmods.dev/badge/skills/mancerayder42/jarvis-os/done/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/mancerayder42/jarvis-os/done"><img src="https://agentmods.dev/badge/skills/mancerayder42/jarvis-os/done.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 | $0.00111 | $0.04190 |
| Opus 5 | $0.00056 | $0.02095 |
| Sonnet 5 | $0.00022 | $0.00838 |
| Haiku 4.5 | $0.00011 | $0.00419 |
Grade A, and why
done 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 4d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/done — Session Wrap-Up
Save a durable record of this session into the hub (see the plugin's hub concept — resolved from JARVIS_HUB env, then ~/.jarvis-hub-path, then ~/jarvis-hub). Scale effort to session weight: light/conversational → minimal note; substantial work (commits, decisions, multi-step) → structured note. Don't fabricate. Don't pad.
Token discipline (read this first)
This skill runs at the end of every session, so cost compounds. Four rules to keep it cheap:
- No narration between tool calls. Don't write "Running command...", "Edit succeeded, continuing...", "Now committing..." — those are wasted tokens. Run tools silently. Only the final confirmation is shown to the user.
- One bash call for context. The resolver script bundles every piece of prep info you need. Don't make additional
git log,ls, orcatcalls unless the resolver output is genuinely missing something. - Skip steps when they don't apply. If the resolver printed no
dirty:lines → no commit step. If session was light → no patterns scan. Iftoday_daily_note=(none)→ no link to it. - Never full-Read
CONTEXT.mdorpatterns.md. Both can grow large over a long-lived hub. Step 4 updatesCONTEXT.mdvia a script (no read); step 5 dedups patterns viagrep(no read). If you ever must touch them directly, useoffset/limit— never load the whole file.
Workflow
1. Resolve context
bash "${CLAUDE_PLUGIN_ROOT}/skills/done/scripts/resolve-context.sh"
The output is a flat key=value block. Key fields you'll use:
hub,sessions_dir,project— where the session note goes and what the work belongs tohub_is_git—nomeans the hub isn't a git repo at all; skip the commit step entirely (see edge cases)hub_dirty— any uncommitted changes anywhere in the hubsessions_dirty,wiki_dirty,memory_dirty,other_hub_dirty— per-area dirt flagsdirty:hub:<path> <count>lines — every dirty top-level path in the hub. This is the authoritative list for what to stage; don't guess from the flags alone.hub_branch/_remote/_upstream/_ahead— push state. See step 6.wiki_recent_count— wiki files modified in the last 24h (informational only)current_branch— branch of the repo you were working in (not the hub) — note it in the session note if relevanttoday_daily_note— path to today's daily note, or(none)(most hubs won't have this — that's fine, skip the line)last_session_note,last_session_date— for continuity contexttoday_session:<path>lines — existing session notes for today (idempotency)commit:<hash> <msg>lines — commits in the hub since last session date
What ships with it
5 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.
- 4d ago Changed · +5 lines 98f4a26e6283
- 10d ago First seen · 248 lines · 111 tokens per session scan A 7d7434230cd0
done is a skill published in the GitHub repository ManceRayder42/jarvis-os (5 stars, last pushed 5d ago), licensed MIT. It adds 111 tokens to every session and 4,190 once invoked, about $0.0006 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
commit
Changelog and commit — lightweight motion for day-to-day plugin dev work in the monorepo. One commit per plugin scope; CHANGELOG and staging routed by detected slug. Trigger when the user says "commit", "commit this", "save this", "wrap this up", "let's commit", or finishes a change and wants to capture it. NOT for…
git-commit
Creates git commits following Conventional Commits format with type/scope/subject. Use when user wants to commit changes, create commit, save work, or stage and commit. Enforces project-specific conventions from CLAUDE.md.
catchup
Restore context after /clear by summarizing recent work and project state.
project-context-sync
Keep a living project state document updated after each commit, so any agent (or future session) can instantly understand where things stand.
git-master
Git expert: atomic commits with style detection, rebase and squash, and history archaeology through blame, bisect and pickaxe.
commit
Commit the current session's changes only, gateway-inline. Session-isolated (never -A, staged set verified against the session list), doc-sync-gated. The gateway runs the commit inline — it already holds the diff, session file list, and change intent; on a mechanical gate hit it judges doc-sync warm in its own context…