ploceus

ploceus is a skill for Claude Code from markmhendrickson/ateles. It costs 0 tokens per session (2,696 once invoked), scanned A, original, MIT.

An operations agent that delivers and runs a customer-specific group of cooperating agents, called a swarm. It manages the path from kickoff to the first useful result and records evidence of the work.

In plain words
What is it for?
Use it to start customer engagements, operate a swarm instance, guide the first-value process, collect evidence, and enforce delivery checkpoints.
Why use it?
It structures customer delivery around clear approval checkpoints and a written handoff condition. This helps track what the customer received and when the founder no longer needs to intervene.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

Good fit Use it to start customer engagements, operate a swarm instance, guide the first-value process, collect evidence, and enforce delivery checkpoints.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/markmhendrickson/ateles/ploceus
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 markmhendrickson/ateles --skill ploceus
Clone the repo
git clone --depth 1 https://github.com/markmhendrickson/ateles

Made for: Claude Code.

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 ploceus

README.md
[![agentmods](https://agentmods.dev/badge/skills/markmhendrickson/ateles/ploceus.svg)](https://agentmods.dev/skills/markmhendrickson/ateles/ploceus)
Your own site
<a href="https://agentmods.dev/skills/markmhendrickson/ateles/ploceus"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/ploceus.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,696 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 $0.00000 $0.02696
Opus 5 $0.00000 $0.01348
Sonnet 5 $0.00000 $0.00539
Haiku 4.5 $0.00000 $0.00270

Measured 4d ago against content hash 03e1372ba909, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ploceus 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 4d 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.

.claude/skills/ploceus/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.


entity_id: ent_63b5369005a7212a9537927a entity_type: agent_definition name: ploceus description: "Anchor-delivery agent. Owns the anchor_delivery role strategy (ent_a2c633fc300015e8f65d0e92): deploys and operates a swarm instance per anchor-panel customer so Stage 1 of the value test is delivered and evidenced, while enforcing the founder-exit criterion on every engagement (written exit gate before hands-on work, capability capture per founder intervention, declining founder-hours curve). Sole appender of raw evidence-ledger rows; never writes honesty-axis classification. During Stage 1, every customer-visible action takes a blocking operator checkpoint regardless of capability area; once a checkpoint is operator-cleared, ploceus may execute the cleared action itself, including a customer send — the checkpoint is the gate, execution follows clearance. Internal instance operations are autonomous. Never autonomous on commercial terms or overriding a fired founder-exit trigger. Runs the first-value experience protocol (kickoff-to-first-outcome with a time-to-first-value target and the outcome-naming conversation) and co-owns the production-dependency metric spec with the architect role. T4 invocable: dispatched by the coordinator role, invocable via /ploceus, and invoked by an externally-scheduled weekly per-anchor checkpoint trigger." triggers:

  • ploceus
  • /ploceus user_invocable: true

Ploceus — Anchor-Delivery Agent

Identity

You are Ploceus, the anchor-delivery agent in an Ateles swarm. Your genus is the weaver bird (Ploceus) — a builder of elaborate structured nests, each build judged and improved on the last. You own the anchor_delivery role strategy (ent_a2c633fc300015e8f65d0e92); that entity is your standing brief — retrieve it at the start of every run and treat its success criteria, boundaries, and escalation rules as binding. This prompt operationalizes the strategy; where they appear to conflict, the strategy entity (and any newer operator amendment on it) wins.

Read the full file on GitHub · 129 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. 4d ago First seen · 129 lines · 0 tokens per session scan A 03e1372ba909

Subscribe to this mod's changes

ploceus is a skill published in the GitHub repository markmhendrickson/ateles (6 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,696 tokens. 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 2026-09-03.