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 injectgit 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/inject)<a href="https://agentmods.dev/skills/ramarahmanda/tsubasa/inject"><img src="https://agentmods.dev/badge/skills/ramarahmanda/tsubasa/inject.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 | $0.00085 | $0.00793 |
| Opus 5 | $0.00043 | $0.00396 |
| Sonnet 5 | $0.00017 | $0.00159 |
| Haiku 4.5 | $0.00009 | $0.00079 |
Grade A, and why
captain-inject 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 8d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Captain inject
The user asserted knowledge. Validate it, connect it, persist it.
Destination is ALWAYS the tsubasa graph (tsubasa event add), never your
private memory directory. The graph is the captain's shared, versioned
memory — it travels with the repo, feeds hot/warm tiers, and is queryable by
every session and teammate. Private memory hides knowledge on one machine.
Steps
- Classify: event type (note/incident/decision/config_change), entities
involved, impact, domains. Run
tsubasa query "<topic>"to find the existing entities and check for conflicts. - Validation gate — restate what you understood in one line:
Recording as <type>, domain=<d>, impact=<i>, links to <entities>[, supersedes <old>]. Correct?- If it contradicts existing knowledge, ask the one WHY question before writing (the answer is the most valuable part of the event).
- On confirmation, append:
tsubasa event add --type <t> --title "..." --impact <i> --domains <d> \ [--supersedes <entity-id>] [--entity id:type:name:desc]... \ [--relation src:pred:tgt]... [--ref kind:id]... --body "<the why>" - Check output for reconciliation notes; if
tsubasa questionshas new open questions relevant to this, raise them now (once, briefly) — otherwise stay silent.
A directory of knowledge, not a single fact
If the user points at a PLACE where knowledge lives ("our postmortems are in docs/incidents", "we keep engineering principles in docs/principles"), register a SOURCE instead of writing one event — the adapter keeps it in sync forever:
tsubasa source add incident docs/incidents
tsubasa source add doc docs/principles --kind principle --impact high
tsubasa source add adr docs/adr
Ask one question if the material is sensitive: "commit these files to the
captain repo, or keep them local-only (--no-commit) with just the distilled
knowledge committed?" Then tsubasa ingest.
Future knowledge (goals)
When the user states intent about the FUTURE — "we plan to", "the goal is",
"by Q4 we want", roadmaps, quotations/procurement for upcoming infra — persist
it as a plan event with a goal entity:
tsubasa event add --type plan --title "..." --entity <goal-id>:goal:"<name>":"<target state>" ...
Open goals never decay out of hot memory and every future plan/design is
checked against them. Resolve later with tsubasa goal set <id> achieved|dropped.
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.
- 8d ago First seen · 65 lines · 85 tokens per session scan A 8cb690133c42
captain-inject is a skill published in the GitHub repository ramarahmanda/tsubasa (8 stars, last pushed 10d ago), licensed MIT. It adds 85 tokens to every session and 793 once invoked, about $0.0004 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.
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.
memory-to-skill
Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under…
levelup-specify
Extract Context Directive Records (CDRs) from the current session after completing work. Identifies reusable patterns (rules, personas, examples, evals) and captures directive compliance cases for team-ai-directives.
change-publish
Promote accepted Change Decision Records (ChDRs) from drafts to project memory at .adlc/memory/chdr/, write OKF-style frontmatter, and regenerate the boot-facing .adlc/memory/chdr.md index that team-boot injects at session start. Use after /change-clarify has accepted ChDRs.
learn
Must be used near the end of any non-trivial turn that produced potentially reusable tools, guidance, errors, workarounds, or workflows, so those lessons are saved for future turns.