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 instructions/ciselyai/agency-skills/agents-mdgit clone --depth 1 https://github.com/CiselyAI/agency-skillsWrote 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/instructions/ciselyai/agency-skills/agents-md)<a href="https://agentmods.dev/instructions/ciselyai/agency-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/ciselyai/agency-skills/agents-md.svg" alt="Measured on agentmods" 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 | $0.01041 | $0.01041 |
| Opus 5 | $0.00521 | $0.00521 |
| Sonnet 5 | $0.00208 | $0.00208 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
agency-skills AGENTS.md 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — model your company in Cisely
This repository is a portable skill package that teaches an AI coding agent to
model a company as a living context graph in Cisely by
driving the Cisely MCP server. It ships as a Claude Code plugin and as
plain, harness-agnostic SKILL.md skills that Codex, Antigravity, Cursor,
OpenCode, Aider, and any other AGENTS.md-aware agent can read.
If you are an agent and the user asks to model, populate, or review their company, personas, strategy, goals, or value proposition in Cisely — read the relevant skill below before acting, and make sure the Cisely MCP is connected first.
The one hard dependency: the Cisely MCP
Everything here works by calling tools on the cisely MCP server at
https://app.cisely.dev/mcp (authenticated over OAuth). Authoring is impossible
without it. Confirm it is connected before you start:
- Claude Code — the plugin registers it; run
/mcp, pick cisely, sign in. - Every other harness — see
docs/install.mdfor the one-line MCP config for your tool. The portable.mcp.jsonat the repo root works for any tool that reads it (via themcp-remotestdio bridge).
If no cisely tools are available in your session, stop and tell the user to
connect the MCP — do not invent business data or write to files as a substitute.
The skills (read the one that matches the task)
| Skill | When to read it |
|---|---|
cisely-agency-model |
The core. Modeling a company's context graph — the response side (mission, beliefs, strategy, initiatives, metrics) and the demand side (personas, operating contexts, stakeholders, goals, expectations). The worldview, the build order, and the MCP tool playbook. Read this whenever the user wants to model, build, populate, or refine their company, personas, strategy, goals, or value proposition. |
cisely-sub-strategy |
Authoring your own strategy kinds (a technology strategy, a GTM strategy, a people-&-culture strategy): define a company-wide schema, publish it, then fill in records nested under a core strategy. |
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.
- 5d ago First seen · 68 lines · 1,041 tokens per session scan A 7a6320432ae0
agency-skills AGENTS.md is an instructions file published in the GitHub repository CiselyAI/agency-skills (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,041 tokens to every session, about $0.0052 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.
Other instructions, from other repositories
living-manual CLAUDE.md
Instructions for dougstanford/living-manual, covering living-manual, start of every session, how work lands — non-negotiable, user's manual (living-manual) and releasing.
ship-it open-pr.instructions.md
Instructions for khrichtchatyi/ship-it: When the user asks to open, create, or submit a pull request, follow the skill in skills/open-pr/SKILL.md in full: verify gh is authenticated, resolve the target repository and default branch, push the current branch, open one pull request with a title and body derived from the…
agent-skills CLAUDE.md
Instructions for mindbox-cloud/agent-skills, covering agent-skills — developer guide for claude code, repository purpose, repository structure, how to add a new plugin and step 1 — create the directory structure.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).