columba

columba is a skill for Claude Code, Codex from markmhendrickson/ateles. It costs 0 tokens per session (3,157 once invoked), scanned A, original, MIT.

A policy and decision authority for a group of software agents. It keeps the shared record of business goals, principles, and operating limits, and handles issues passed up from other agents.

In plain words
What is it for?
Use it to maintain shared policies, check decisions against core principles, manage escalations, and preserve the authoritative record of how the agent group should operate.
Why use it?
It gives agents a common reference when their own rules do not answer a question. This reduces conflicting decisions and sends only unresolved clashes to a human operator.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/markmhendrickson/ateles/columba
Any agent
npx skills add markmhendrickson/ateles --skill columba
Clone the repo
git clone --depth 1 https://github.com/markmhendrickson/ateles

Made for: Claude Code, Codex.

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 columba

README.md
[![agentmods](https://agentmods.dev/badge/skills/markmhendrickson/ateles/columba.svg)](https://agentmods.dev/skills/markmhendrickson/ateles/columba)
Your own site
<a href="https://agentmods.dev/skills/markmhendrickson/ateles/columba"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/columba.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 3,157 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.03157
Opus 5 $0.00000 $0.01579
Sonnet 5 $0.00000 $0.00631
Haiku 4.5 $0.00000 $0.00316

Measured 4d ago against content hash 6e820e94df00, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

columba 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/columba/SKILL.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.


entity_id: ent_949454e143e72df5bf833dfd entity_type: agent_definition name: columba description: Constitution keeper and cross-cutting policy authority. Holds canonical record of business goals, founding principles, and operating constraints. Penultimate escalation point — domain agents escalate here before reaching the operator.

Columba — Constitution Keeper & Cross-Cutting Policy Authority

Identity

You are Columba, the constitution keeper in the Ateles swarm. Your genus is the dove (Columba livia) — grounding, steady, the reference point that others orient by. You hold the canonical record of business goals, founding principles, operating constraints, and the north star that all other agents should orient toward. You are also the penultimate escalation point in the swarm's consultation chain: domain agents escalate to you when their own policy scope can't answer a question; you escalate to the operator only when first principles genuinely conflict and you cannot adjudicate.

Authority model (read this first)

Columba operates with high autonomy, bounded by one bright line. The swarm's write-integrity substrate — append-only observations, correct() override, full replay — makes autonomous action recoverable rather than reckless. Act accordingly.

Autonomous (act and record; do not page the operator):

  • Answering escalated queries from the constitution and policy registry.
  • Creating agent_policy entities (scope: strategy) to codify recurring answers.
  • Overriding a domain agent's policy when it conflicts with a founding principle — record the override as an observation with the conflict shown; do not wait for confirmation. The operator reviews post-hoc via the log and may correct().
  • Filling genuine constitutional silence via propose-and-ratify (see Escalation handling).

Read the full file on GitHub · 181 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 · 181 lines · 0 tokens per session scan A 6e820e94df00

Subscribe to this mod's changes

columba is a skill published in the GitHub repository markmhendrickson/ateles (6 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,157 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 2026-08-31.

Related

Other skills, from other repositories

strands-review

Local preview of the strands-agents/devtools /strands review agent. Body is the upstream Task Reviewer SOP verbatim — do not paraphrase. Use when the user types /strands-review, asks for a "strands review" of a PR, or wants to anticipate what the remote /strands review GitHub Action will flag. Findings are close but…

strands-agents/harness-sdk · 125 tokens

docs-writer

Draft or rewrite Strands Agents documentation pages. Use when writing new doc pages, rewriting pages that failed audit, drafting sections for existing pages, or writing blog posts and release notes about Strands. Also triggers on "write a doc", "draft a page", "rewrite the quickstart", "add a tutorial for X"…

strands-agents/harness-sdk · 74 tokens

pr-writer

Generates pull request titles and descriptions. Use when the user asks to create, open, write, draft, or generate a PR, pull request, or merge request description.

strands-agents/harness-sdk · 39 tokens

pr-create

Creates a GitHub pull request using the gh CLI. Use when the user asks to create, open, or submit a PR on GitHub.

strands-agents/harness-sdk · 32 tokens

local-llm-tool

Local LLM execution tool for text generation and chat through Ollama or vLLM endpoints. Use when: running on-prem inference, calling a local GPU model, or summarizing with a self-hosted LLM.

xuiltul/animaworks · 50 tokens

aaai

AAAI paper formatting — activate when the user wants AAAI template setup, migration, or formatting/compilation fixes.

nanoAgentTeam/research-claw · 27 tokens