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 skills add bradfeld/ceos --skill ceos-idsgit clone --depth 1 https://github.com/bradfeld/ceosWrote 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/bradfeld/ceos/ceos-ids)<a href="https://agentmods.dev/skills/bradfeld/ceos/ceos-ids"><img src="https://agentmods.dev/badge/skills/bradfeld/ceos/ceos-ids/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/bradfeld/ceos/ceos-ids"><img src="https://agentmods.dev/badge/skills/bradfeld/ceos/ceos-ids.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00019 | $0.02508 |
| Opus 5.5 | $0.00008 | $0.01003 |
| Sonnet 5.5 | $0.00004 | $0.00502 |
| Haiku 4.5 | $0.00002 | $0.00251 |
Grade A, and why
ceos-ids 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 1mo 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ceos-ids
Run the IDS (Identify, Discuss, Solve) process — the EOS method for resolving issues systematically. Every issue gets a root cause, a focused discussion, and at least one To-Do with an owner and due date.
When to Use
- "We have an issue" or "add to the issues list"
- "IDS this" or "let's identify discuss solve"
- "What are our open issues?" or "show the issues list"
- "Solve [issue]" or "discuss [issue]"
- "Close this issue" or "mark [issue] as solved"
- During L10 meetings when the IDS section begins
- Any time the team needs structured problem-solving
Context
Finding the CEOS Repository
Search upward from the current directory for the .ceos marker file. This file marks the root of the CEOS repository.
If .ceos is not found, stop and tell the user: "Not in a CEOS repository. Clone your CEOS repo and run setup.sh first."
Sync before use: Once you find the CEOS root, run git -C <ceos_root> pull --ff-only --quiet 2>/dev/null to get the latest data from teammates. If it fails (conflict or offline), continue silently with local data.
Key Files
| File | Purpose |
|---|---|
data/issues/open/ |
Open issues awaiting resolution |
data/issues/solved/ |
Resolved issues (archive) |
templates/issue.md |
Template for new issue files |
Issue File Format
Each issue is a markdown file with YAML frontmatter:
id: issue-001
title: "Slow customer onboarding"
priority: 1 # 1 (highest) - 5 (lowest)
category: process # people | process | data | vision | traction
ids_stage: identified # identified | discussed | solved
created: "2026-02-06"
Priority levels:
1— Critical, solve first2— High, solve soon3— Medium, solve when time allows4— Low, solve if capacity allows5— Nice-to-have, backlog
Categories (the 5 EOS issue types):
people— right person, right seat issuesprocess— systems, workflows, efficiencydata— metrics, reporting, information gapsvision— alignment with V/TO, Core Focustraction— execution, accountability, follow-through
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.
- 1mo ago First seen · 263 lines · 19 tokens per session scan A fb91c1b84296
ceos-ids is a skill published in the GitHub repository bradfeld/ceos (159 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 2,508 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.