captain-inject

captain-inject is a skill for Claude Code from ramarahmanda/tsubasa. It costs 85 tokens per session (793 once invoked), scanned A, original, MIT.

A skill for recording confirmed facts about a system in the `tsubasa` knowledge graph, which is shared, versioned project memory. It classifies each fact as a note, incident, decision, or configuration change and connects it to related entities.

In plain words
What is it for?
Use it when the user says to remember something, corrects the project history, explains an outage, changes a system choice, or provides environment and team information.
Why use it?
It prevents important explanations, corrections, deployment details, and incident causes from remaining only in one conversation or one person’s private memory. It also checks for conflicts with existing knowledge before recording the fact.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the tsubasa plugin — 5 skills, 4 hooks shipped together

Good fit Use it when the user says to remember something, corrects the project history, explains an outage, changes a system choice, or provides environment and team information.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ramarahmanda/tsubasa/inject
Install

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.

Any agent
npx skills add ramarahmanda/tsubasa --skill inject
Clone the repo
git clone --depth 1 https://github.com/ramarahmanda/tsubasa

Made for: Claude Code.

Or install tsubasa, the plugin that ships this one along with the rest of its 5 skills, 4 hooks.

Wrote 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.

agentmods badge for captain-inject

README.md
[![agentmods](https://agentmods.dev/badge/skills/ramarahmanda/tsubasa/inject.svg)](https://agentmods.dev/skills/ramarahmanda/tsubasa/inject)
Your own site
<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>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 793 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 8d ago against content hash 8cb690133c42, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

plugin/skills/inject/SKILL.md · 65 lines

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

  1. 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.
  2. 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).
  3. 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>"
  4. Check output for reconciliation notes; if tsubasa questions has 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.

Read the full file on GitHub · 65 lines

Changes

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.

  1. 8d ago First seen · 65 lines · 85 tokens per session scan A 8cb690133c42

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories

decision

Single entry point for all decision operations: capture, search, manage. Routes based on natural language intent.

zimalabs/code-decisions · 23 tokens

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.

TerminallyLazy/tree-ring-memory-claude-plugin · 38 tokens

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…

zilliztech/memsearch · 82 tokens

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.

tikalk/adlc-team-skills · 46 tokens

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.

tikalk/adlc-team-skills · 73 tokens

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.

AgentToolkit/altk-evolve · 40 tokens