Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/iamcxa/kc-claude-pluginsnpx agentmods add skills/iamcxa/kc-claude-plugins/first-officerWrote 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/iamcxa/kc-claude-plugins/first-officer)<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/first-officer"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/first-officer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/first-officer"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/first-officer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00068 | $0.00517 |
| Opus 5 | $0.00034 | $0.00259 |
| Sonnet 5 | $0.00014 | $0.00103 |
| Haiku 4.5 | $0.00007 | $0.00052 |
Grade A, and why
first-officer 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 2d 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
kc-ship-flow first officer
docs/ship/README.md's ## Local Profile table is this skill's declared input before resolving
or dispatching a batch, not the full README as a policy bundle. local-profile-check.py below
verifies the table's required rows; nothing checks what else this skill reads.
Refuse before dispatch
Run:
python3 kc-ship-flow/scripts/local-profile-check.py docs/ship/README.md
A non-zero exit names the missing row on stderr. Do not dispatch a batch while this refuses —
most commonly the Runtime row, which selects local subagent or Conductor cloud dispatch for
the stage that follows.
Run the station chain
Advance one commissioned docs/ship batch entity through its six stages in order, calling each
stage's installed script from docs/ship/README.md's per-stage lines:
dispatched—kc-ship-flow/scripts/fenced-dispatch.shaccepted—kc-ship-flow/scripts/accept-evidence.shreviewed—kc-ship-flow/scripts/open-pr.sh, thenkc-ship-flow/scripts/disposition.pyuat(gate) —kc-ship-flow/scripts/e2e-gate.py,kc-ship-flow/scripts/uat-doc.py,kc-ship-flow/scripts/notify.shmerged— no kc-ship-flow script; observe the GitHub merge through Spacedock'spr-mergemodclosed—kc-ship-flow/scripts/dev-debrief.py, thenkc-ship-flow/scripts/ship-debrief.py
Write and check each stage's pin with kc-ship-flow/scripts/pin.py write --station <name> /
check --station <name> before advancing past it. Validate the closed stage's close receipt with
docs/plan-flow/schema/validate-receipt.py <plan-receipt.json> <approval.json> <close-receipt.json>
before terminalizing the entity.
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.
- 2d ago First seen · 41 lines · 68 tokens per session scan A 6e9175b58e44
first-officer is a skill published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 517 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 2026-09-06.
Other skills, from other repositories
workflow-integration-test-green
Codex uses static project-reference loading instead of runtime-injected project docs. When coding, planning, debugging, testing, or reviewing, open project docs explicitly using this routing.
aem-qa-handoff
Post QA handoff comment to ADO with QA page URLs, prerequisites, and wiki link. Reuses test page from /aem-doc-gen if available, otherwise creates its own on QA AEM. Use after /aem-doc-gen and /dx-doc-gen.
evidence-publish
Deliver a QA/evidence packet to a tracker or keep it local, behind an always-ask preview gate. Protocol for /orc:qa Phase 6, /orc:evidence, and any evidence-delivery step.
testrail
Sincronizar testes com TestRail. Use quando o usuário mencionar "testrail", "gestão de testes", "casos de teste", "execução de testes", "sincronizar casos de teste", "enviar resultados para testrail" ou "importar do testrail".
workflow-qa
A quality-assurance procedure for testing Workflow documents and features in their real online environment. QA means checking whether software behaves as expected and recording evidence.
qshipcheck
Validates that all orchestrator Phase 2 (review), Phase 3 (acceptance), and Phase 4 (deliver) steps were executed after qship pipeline completion. Run this after qship finishes to catch any skipped steps.