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 fixgit 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/fix)<a href="https://agentmods.dev/skills/martineserios/thebrana/fix"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/fix.svg" alt="Measured on agentmods" 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 | $0.03087 |
| Opus 5 | $0.00019 | $0.01543 |
| Sonnet 5 | $0.00008 | $0.00617 |
| Haiku 4.5 | $0.00004 | $0.00309 |
Grade B, and why
fix scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat > ~/.claude/run-state/active-goal.json <<JSON How it starts
The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix
Structured bug fixing workflow. Five steps: REPRODUCE → DIAGNOSE → FIX → VERIFY → COMMIT → (HARDEN). Enforces test-first debugging — no source changes until a failing test exists. HARDEN is optional: fires when the same errata class has appeared 2+ times — offers to convert the pattern into a PreToolUse gate.
Usage
/brana:fix [task-id or bug description]
If a task ID is provided, load it via brana backlog get <id> and use the description as the bug statement.
Step Registry
On entry, create CC Tasks for each step (for compression resilience):
TaskCreate: "/brana:fix — REPRODUCE"
TaskCreate: "/brana:fix — DIAGNOSE" (blocked by REPRODUCE)
TaskCreate: "/brana:fix — FIX" (blocked by DIAGNOSE)
TaskCreate: "/brana:fix — VERIFY" (blocked by FIX)
TaskCreate: "/brana:fix — COMMIT" (blocked by VERIFY)
TaskCreate: "/brana:fix — HARDEN" (blocked by COMMIT, optional)
Mark each in_progress when starting, completed when done. Resume after compression by calling TaskList and finding the in_progress step.
After creating the step registry, call /goal and write active-goal.json unless --no-goal was passed.
If a task_id is known, first extract AC: lines from task context:
brana backlog get {task_id} | python3 -c "
import json, sys
t = json.load(sys.stdin)
lines = [l[3:].strip() for l in (t.get('context') or '').splitlines() if l.startswith('AC:')]
print('\n'.join(lines))
"
- If AC: criteria found:
Pin/goal "fix {task-id} — Done when: {criteria joined with ' AND '}"base_refat goal start and initializetests_required[]empty (hardened form — ADR-061 §4, identical to build's LOAD step 0):base_ref=$(git -C "{git_root}" rev-parse HEAD) cat > ~/.claude/run-state/active-goal.json <<JSON {"task_id": "{task_id}", "cwd": "{git_root}", "session_id": "$BRANA_SESSION_ID", "base_ref": "$base_ref", "criteria": ["{criterion1}", "{criterion2}"], "tests_required": []} JSONbase_refanchors the grader-immutability check; the REPRODUCE failing test is committed red in its own commit (the REPRODUCE step, Step 1) so thered-verificationpre-commit hook (t-2216) registers it intotests_required[]— earning the exemption by observed redness. The Stop hook (goal-completion.sh) auto-completes the task when all criteria pass, behind the presence + immutability interlocks.
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 First seen · 263 lines · 38 tokens per session scan B 17ed4ba95bc9
fix 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 3,087 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
a0-debug-plugin
Diagnose and fix Agent Zero plugin problems. Covers plugin not appearing, won't enable, API endpoints not responding, frontend store errors, extension point injection, settings resolution, hooks.py issues, and log inspection. Use when a plugin is not working, not loading, crashing, missing from the list, or behaving…
a0-debug-plugin
Diagnose and fix Agent Zero plugin problems. Covers plugin not appearing, won't enable, API endpoints not responding, frontend store errors, extension point injection, settings resolution, hooks.py issues, and log inspection. Use when a plugin is not working, not loading, crashing, missing from the list, or behaving…
bug-fix-workflow
Structured bug diagnosis and repair workflow using the 5-Whys root cause analysis method. Ensures fixes include tests, documentation, and knowledge capture.
triage-bug
Use when triaging a bug from session evidence (evidence-capture JSONL, replay JSONL, telemetry, repo-audit) instead of from a live user description, and producing a TDD fix plan plus a docs/bugs/{slug}.md triage artifact.
debug
Use when something is broken — a failing or flaky test, crash, wrong result or regression — and the root cause must be reproduced and proven before any fix. On-demand; callable mid-implement. NOT a feature to spec or build (that is specify/implement), NOT the lint/test gate (that is verify), NOT adversarial diff…
systematic-debug
4-phase root cause analysis and debugging.