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 martineserios/thebrana --skill closegit clone --depth 1 https://github.com/martineserios/thebranaWrote 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/martineserios/thebrana/close)<a href="https://agentmods.dev/skills/martineserios/thebrana/close"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/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/martineserios/thebrana/close"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/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 | $0.00038 | $0.03645 |
| Opus 5.5 | $0.00015 | $0.01458 |
| Sonnet 5.5 | $0.00008 | $0.00729 |
| Haiku 4.5 | $0.00004 | $0.00364 |
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 1mo 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Close — Session End
End a work session. Extracts what was learned, writes a handoff note for the next session, stores patterns, and detects doc drift. Replaces /session-handoff close mode and /debrief.
When to use
- User says "done", "bye", "closing", "that's it", or similar
- End of a long implementation session
- Before switching to a different project
- Mid-session, on demand — context relief before
/compact, switching tasks, capturing a discovery, abandoning an approach - Explicitly:
/brana:close [--<orientation>]
Orientation modes (ADR-053)
WHY you're closing picks WHAT runs. Flag given → execute immediately, no questions. Bare /brana:close → the gate detects the scenario and asks (options labeled with their flags — the picker teaches them).
| Flag | Use when | What happens |
|---|---|---|
--continue |
pausing to resume — context relief, task switch | snapshot + queue + resumable handoff; task stays in_progress; no cleanup |
--finish |
work is done | snapshot + queue + handoff; task → completed; cleanup runs; extraction tonight |
--patterns |
a discovery is worth keeping, regardless of task state | inline extraction (Steps 4–5) NOW; no queue, no handoff, no task/git changes |
--abort |
approach proven wrong | reason required; branch archived as pushed aborted/* tag via close-abort.sh; task → pending |
Deferred (post-v1): --block, --handoff, --eod — see ADR-053.
Phase Protocol — how to execute this skill
The procedure body lives in per-phase files under phases/ (this skill's base directory). Never execute a phase from memory. Three rules:
- On skill entry: Read
phases/gate-and-evidence.mdfirst — always. It classifies the close weight (NANO/LIGHT/FULL); everything downstream depends on it. - At every step boundary: when a phase completes and the next begins, Read the next phase file from the PHASES registry below BEFORE doing any of its work. A phase you have not Read this session does not exist — do not improvise its steps.
- On resume after compression: identify your current step (CC TaskList
/brana:close — {STEP}entries), then Read the phase file that owns that step before continuing. Previously loaded phase content did NOT survive compression. Re-read../_shared/guided-execution.mdtoo.
What ships with it
10 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.
- phases/cleanup.md 9.5 KB
- phases/close-mode-and-evidence.md 15 KB
- phases/doc-drift.md 4.3 KB
- phases/errata-and-patterns.md 8.6 KB
- phases/gate-and-evidence.md 23 KB
- phases/initiative-accumulator.md 12 KB
- phases/metadata-and-memory.md 5.8 KB
- phases/notes-and-ideation.md 11 KB
- phases/propagate.md 7.1 KB
- phases/session-state.md 18 KB
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.
- 1mo ago Changed · -1 lines 3c5843f1f191
- 1mo ago Changed · +2 lines 028a3d7de576
- 1mo ago First seen · 161 lines · 38 tokens per session scan A 111ca2af4c19
close is a skill published in the GitHub repository martineserios/thebrana (3 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 3,645 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
session-close
Use at a session boundary — the session looks done, or you are breaking mid-work. Routes by fulfillment: goal delivered whole → done-close (closeout moves + this session's carry file cleared); in-motion remainder → park-close (card-anchored remainder appended as a ## Progress block on the owning card, only what no…
session-continue
Use at session start to resume in-flight work — reads the root SESSION-STATE/ carry ledger and orients. Carries present → pick one (surface the list when several sessions are in flight), follow its Read first into the card it names and read the latest block of each type as the lead, reconstruct where work stopped +…
writing-handoff
Use when an auto-compaction system reminder appears, when the user explicitly invokes /handoff or asks to "write a handoff" / "save state", or when the user signals they're near the context limit specifically ("running low on context", "almost out of context", "context is getting full"). Do NOT fire on general…
sw-learn
Captures patterns and learnings from the current work unit. Reviews build failures, gate findings, and architecture decisions. Applies objective promotion criteria autonomously — patterns.md is the artifact.
context-memory
Saves and searches past Claude Code sessions so context, decisions, and code persist across conversations. Use when user says 'remember this', 'save this session', 'recall', 'search past sessions', 'what did we discuss about', or 'find previous work on'. Do NOT use for general file storage, note-taking, or bookmark…
writing-style
Use for technical communication - GitHub/GitLab tickets, PR/MR descriptions, issue comments, code review comments, commit messages. Direct, brief style with no AI-speak. NOT for README.md, public docs, or blog posts.