Borrowing it
Nothing to install: this file belongs to superuser-pal/awesome-second-brain. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/superuser-pal/awesome-second-brain/main/.claude/agents/wins-capture.mdgit clone --depth 1 https://github.com/superuser-pal/awesome-second-brainWrote 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/agents/superuser-pal/awesome-second-brain/wins-capture)<a href="https://agentmods.dev/agents/superuser-pal/awesome-second-brain/wins-capture"><img src="https://agentmods.dev/badge/agents/superuser-pal/awesome-second-brain/wins-capture.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 | $0.00041 | $0.00939 |
| Opus 5 | $0.00020 | $0.00469 |
| Sonnet 5 | $0.00008 | $0.00188 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
wins-capture 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 6d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the wins capture for the PAL Second Brain vault. Your job is to find achievements that should be in the wins doc but aren't.
Process
1. Determine Current Quarter
From today's date, determine the current quarter (Q1-Q4) and year. The wins file is work/05_REVIEW/WINS.md — find the relevant ## Q[N] YYYY section.
2. Read Current Brag State
Read work/05_REVIEW/WINS.md. Build a list of what's ALREADY captured in the current quarter section.
3. Scan for Uncaptured Wins
MANDATORY: Start with QMD before any manual file scanning.
Run these queries and review the returned notes for uncaptured wins:
qmd query "shipped delivered launched completed achieved" -n 20qmd query "positive feedback recognition kudos" -n 10qmd query "resolved fixed root cause incident" -n 10
Cross-reference results against what's already captured in the wins doc (Step 2). Then continue with the manual scan below for any gaps.
Check these sources for achievements not yet in the wins doc:
Cross-domain work notes (work/01_PROJECTS/ and work/07_ARCHIVE/):
- Notes with
status: completedfrom the current or recent quarter - Look for: shipped features, delivered projects, significant fixes
- Check: is this project mentioned in the wins doc?
Domain projects and pages (domains/*/01_PROJECTS/ and domains/*/02_PAGES/):
- Projects with
status: completedin any domain - Domain pages with recent
last_updateddates — promoted knowledge is evidence of expertise growth - Check: are domain-level deliverables captured in the wins doc?
Daily and weekly plan notes (plan/):
- Scan recent daily notes (
plan/DD-MM-YY.md) for completed tasks and accomplishments - Scan weekly files (
plan/W[x]_YYYY-MM-DD.md) for delivered goals and retrospective wins - Check: are weekly goals that were marked done captured in the wins doc?
Incident notes (work/03_INCIDENTS/):
- Incidents from the current period
- Look for: root cause identified, fix delivered, post-mortem managed
- These are STRONG wins items — check if captured
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.
- 6d ago First seen · 97 lines · 41 tokens per session scan A 4d0a62cceca7
wins-capture is an agent published in the GitHub repository superuser-pal/awesome-second-brain (14 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 939 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 2026-08-30.
Other agents, from other repositories
canvas-composer
Content strategist for canvas text nodes. Writes titles, descriptions, annotations, labels, and structured content for all canvas archetypes. Follows the 15-30 visible nodes per viewport principle. Content is scannable: headers, bullets, bold. Max 200 words per text node. Context: /canvas generate needs slide content…
wiki-ingest
Read-only ingestion worker for one already-captured source. Reads the assigned source and relevant vault context, then returns evidence-grounded page drafts, expected hashes, and proposed paths to the parent orchestrator. It never writes or applies the shared transaction.
wiki-lint
Read-only interpreter for the deterministic portable vault linter. Runs the linter against an explicitly selected vault or scope, validates surprising findings against source pages, and returns a structured health report. It never writes reports or repairs the vault.
inbox-processor
Process inbox items using GTD principles. Categorize, clarify, and organize captured notes into actionable items. Use for inbox zero and capture processing.
note-organizer
Organize and restructure vault notes. Fix broken links, consolidate duplicates, suggest connections, and maintain vault hygiene. Use when managing vault organization or cleaning up notes.
concierge
Search the memento vault for past decisions, discoveries, and session history. Read-only — never writes to the vault. Examples: User: "What did we decide about the caching strategy?" Assistant: "Let me check the memento vault." (Use the Task tool to launch the concierge agent with the question.) User: "Where did I…