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 ramarahmanda/tsubasa --skill capturegit clone --depth 1 https://github.com/ramarahmanda/tsubasaWrote 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/ramarahmanda/tsubasa/capture)<a href="https://agentmods.dev/skills/ramarahmanda/tsubasa/capture"><img src="https://agentmods.dev/badge/skills/ramarahmanda/tsubasa/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 | $0.00058 | $0.00528 |
| Opus 5 | $0.00029 | $0.00264 |
| Sonnet 5 | $0.00012 | $0.00106 |
| Haiku 4.5 | $0.00006 | $0.00053 |
Grade A, and why
captain-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 7d 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.
What it actually says
Captain capture
A decision was just accepted in conversation. Persist it — this is the moment that makes the Captain the one who "remembers everything".
Steps
- Determine: decision title, domain(s), impact (high/medium/low), which
existing entities it touches, and whether it supersedes a previous decision
(check
tsubasa query "<topic>"first). Also checktsubasa goal list— every plan/design must state, in one line, how it aligns or conflicts with each relevant open goal ("supports goal-decommission-legacy-sso" / "⚠ conflicts with goal-x because…"). Link supporting work with a--relation <adr>:works_toward:<goal-id>. - Validation gate — one line, before writing anything:
Saving: adr-<slug>, links to <entities>[, supersedes <old>]. OK?If it supersedes something recent or load-bearing, ask the one question that captures the WHY (e.g. "that ADR chose Kafka for ordering — has that requirement changed?") and put the answer in the event body. - On confirmation:
- Draft the ADR at
docs/adr/adr-<slug>.md(title, status: accepted, date, context, decision, consequences — cite prior incidents/ADRs from the graph). tsubasa event add --type decision --title "..." --impact <i> --domains <d> \ --ref adr:adr-<slug> [--supersedes <old-entity-id>] \ --entity adr-<slug>:adr:"<title>":"<one-line>" --body "..."
- Draft the ADR at
- Tell the user the branch convention: include
adr-<slug>in the branch or PR name so the work threads back to this decision.
Rules
- ADR ids:
adr-<kebab-slug>, stable forever, they are the thread that links decision → branch → PR → code. - Never store secret values; secret-refs only (name/location).
- One decision = one event. Do not batch.
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.
- 7d ago First seen · 40 lines · 58 tokens per session scan A 44c79be7612f
captain-capture is a skill published in the GitHub repository ramarahmanda/tsubasa (8 stars, last pushed 9d ago), licensed MIT. It adds 58 tokens to every session and 528 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
decision
Single entry point for all decision operations: capture, search, manage. Routes based on natural language intent.
repo-standard
Use when working in a RepoKit-compliant repo — about to commit or open a PR, adding a learning / ADR, or asking "where does X go" or "what's the convention here". Loads the RepoKit conventions and the pre-commit / pre-PR checklists.
tree-ring-memory
Guides AI agents in using Tree Ring Memory for durable recall, project decisions, user preferences, warnings, future seeds, privacy-safe memory capture, and lifecycle-aware forgetting.
openlore-brainstorm
Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.
mission-brief
Mission-driven SDD orchestrator: take a feature description, structure it into a Mission Brief (goal, constraints, success criteria), generate an ordered step list with prompts that trigger installed SDD skills via model invocation or command-file discovery, and walk those steps to converged implementation. Use when…
levelup-publish
Compile accepted Context Directive Records (CDRs) into team-ai-directives artifacts and create a draft PR. Builds context modules, evals goldensets, and/or skills based on CDR context types.