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 martineserios/thebrana/plugin install branaWrote 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/log)<a href="https://agentmods.dev/skills/martineserios/thebrana/log"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/log/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/log"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/log.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 | $0.00031 | $0.02061 |
| Opus 5.5 | $0.00012 | $0.00824 |
| Sonnet 5.5 | $0.00006 | $0.00412 |
| Haiku 4.5 | $0.00003 | $0.00206 |
Grade A, and why
log 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Log — Event Capture
Append-only event log. The lowest-friction entry point into brana — no need to know tasks.json schema, pipeline stages, or memory conventions. Just /brana:log "something happened".
When to use
- Something happened (call, meeting, idea, observation) and you want to record it
- You received links or references to capture for later
- Pasting a WhatsApp or chat dump to triage
- Anything that doesn't fit
/brana:backlog add(not a commitment yet) or/brana:pipeline(not a qualified lead yet)
Commands
/brana:log "text with optional #tags" — quick append
/brana:log bulk — paste multi-line content, parse + deduplicate
File
Per-project log with global fallback.
Resolution order
- CWD project:
git rev-parse --show-toplevel→ basename → find matching CC project memory dir →{dir}/event-log.md - Tag routing: if entry has
#projectslugmatching a registered project intasks-portfolio.json, route to that project's log - Global fallback:
~/.claude/memory/event-log.md— when no project context is detected
Finding the CC project memory dir
~/.claude/projects/-{sanitized-path}/memory/event-log.md
Where sanitized-path is the absolute project path with / replaced by - and leading -. Example: project at /home/user/enter_thebrana/thebrana → ~/.claude/projects/-home-user-enter-thebrana-thebrana/memory/event-log.md.
Create the file on first use if it doesn't exist.
/brana:log "text"
Quick append — the default mode.
Steps
-
Parse input. Extract the quoted text from the argument.
-
Extract tags. Find all
#wordtokens in the text. Remove the#prefix and collect as tags. Leave the#taginline in the entry text — tags are visible, not hidden metadata. -
Resolve the log file using the resolution order above (CWD project → tag routing → global fallback). Read it.
- If it doesn't exist, create it with a header:
# Event Log
- If it doesn't exist, create it with a header:
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 First seen · 204 lines · 31 tokens per session scan A e7499f697156
log is a skill published in the GitHub repository martineserios/thebrana (3 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 2,061 once invoked, about $0.0001 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
github-issue-triage
A GitHub issue organiser for open problems and requests in a software project. GitHub is a service where teams store code and track issues.
log
Capture front door. Logs 1..N observations as card files at docs/work/{ID}.md (BUG / DEBT / GAP), gateway-inline — no dispatch. Use when the user says "log this", "track that", "note this down", or types /super-bootstrap:log — and when Claude needs to file its own findings (out-of-scope findings from a review, audit…
Board Meeting Prep
Prepare board meeting decks, updates, and materials for effective governance.
sdd-implement
Execute one or more tasks from the SDD task list. Use when the user says 'implement task', 'execute task', 'build task', 'do TASK-001', 'next task', 'start implementing', or wants to work on specific tasks. Reads only task blocks and their listed files. Auto-batches small tasks when possible.
sw-status
Shows current Specwright state for this worktree, the attached work, repo-wide active works, gate results, and lock status. Supports --reset, --cleanup, and --repair {unitId}.
sdd-status
Show current SDD state and progress at a glance. Use when the user says 'status', 'where are we', 'where we left off', 'session recovery', 'what's the progress', or wants a quick overview of feature and task progress. Ultra-lightweight — reads only state.json.