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 agentmods add skills/agentculture/fleet-cli/communicatenpx skills add agentculture/fleet-cli --skill communicategit clone --depth 1 https://github.com/agentculture/fleet-cliWhat 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 | $0.00184 | $0.03681 |
| Opus 5 | $0.00092 | $0.01840 |
| Sonnet 5 | $0.00037 | $0.00736 |
| Haiku 4.5 | $0.00018 | $0.00368 |
Grade A, and why
communicate 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 yesterday.
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.
This is a copy
95% identical to communicate — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Communicate (Cross-Repo + Mesh)
Steward's job is alignment across the AgentCulture mesh; that surfaces in four distinct channels:
- Tracked, async hand-offs — a gap in another repo (a missing public
API, a divergent skill, a documentation ask) where an agent on the
other side needs to act, and the ask should outlive the conversation.
→
post-issue.sh(GitHub). - Follow-up on a tracked thread — a status update, an answer to a
question, or a "this is done" note on an issue that's already open.
→
post-comment.sh(GitHub). - Inbound state read — pulling current issue body + comments from a
sibling repo so a brief or plan can inline what's there instead of
saying "see issue #N." →
fetch-issues.sh(GitHub). - Ephemeral coordination — a status ping, a question, a "PR ready
for merge" notice on a Culture mesh channel where the audience is
already listening.
→
mesh-message.sh(Culture IRC).
All four live under one skill because they share the same audience (sibling-repo agents) and the same red flag (don't double-post the same ask across post + mesh — pick one).
Backed by agtag
The three GitHub verbs (post-issue.sh, post-comment.sh,
fetch-issues.sh) are thin wrappers around the agtag CLI
(agtag issue post|reply|fetch). agtag handles auto-signature
resolution from the local culture.yaml (falling back to repo
basename), JSON output mode, and a uniform exit-code policy. Read
agtag learn for the agent-facing self-teaching prompt and
agtag explain agtag / agtag explain issue for the surface docs —
this SKILL.md does not re-document agtag's flags.
mesh-message.sh stays a culture channel message wrapper for now;
agtag mesh transport is slated for v0.2.
When to Use
Issue mode (post-issue.sh)
- A gap surfaces in another repo's surface (missing public API, wire-format compat fix, divergent skill, documentation ask).
- You're handing off a self-contained brief to a sibling-repo agent.
- (steward-specific — supplier role.) You're onboarding a sibling to the
stack — "set it up", "align it", "update it with our stack", "set up the
pipelines". The deliverable is an issue with a self-contained brief, never
files written into that repo. In steward, quote steward's
docs/sibling-pattern.md(required artifacts) anddocs/skill-sources.md(the skill set to vendor) into the brief so it stands alone; steward'sCLAUDE.md"Steward's lane" section is the canonical statement. Downstream vendors of this skill don't onboard siblings — those steward-side docs don't exist in your repo, so skip this bullet. - You're asking a question that benefits from a tracked artifact rather than ephemeral chat.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 337 lines · 184 tokens per session scan A d61828657969
communicate is a skill published in the GitHub repository agentculture/fleet-cli (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 184 tokens to every session and 3,681 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to communicate, differing in 8 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…