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 | $0.03664 |
| Opus 5 | $0.00019 | $0.01832 |
| Sonnet 5 | $0.00008 | $0.00733 |
| Haiku 4.5 | $0.00004 | $0.00366 |
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 — 163 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 9.7 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.
- 3d ago Changed · +2 lines 028a3d7de576
- 5d 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 today), licensed MIT. It adds 38 tokens to every session and 3,664 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
taiyi-compress
A workflow tool for shrinking large coding-agent conversations and work files into shorter context notes. It can also coordinate separate agents for parallel development and create handoff notes for continuing work in a new session.
memory
Unified read-side memory operations including knowledge graph search, session context loading, decision timeline viewing, and Mermaid graph visualization. Subcommands: search, load, history, viz, status. Complements /ork:remember (write-side). Use when searching past decisions, loading context, or visualizing the…
context-doctor
Reduces token waste in Claude Code sessions across two axes — context footprint (auto-generates .claudeignore, guides over-read files and /clear timing) and command output (routes to a command-output proxy/hook such as rtk to trim verbose CLI stdout). In hub environments, regularly audits bloated…
ucai-patterns
Use when the user asks about Claude Code best practices, how to write agents, how to use hooks, how to manage context, or how to work effectively with Claude Code's native systems.
salience-splitter
Splits an over-loaded always-loaded context asset (SKILL.md, CLAUDE.md, memory index) into a lean resident layer plus an on-demand layer, by when content is needed rather than by length, linked by imperative pointers. Alias: skill-splitter. Triggers: "SKILL.md too large", "split this skill", "skill is bloated", "skill…
memory-curator
Use at session-close when a session captured several new memories, or on-demand, to consolidate, deduplicate, prune, and structure the beads memory store. Triggers on "curate memories", "clean up memories", "memory sweep".