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 commands/nxtg-ai/forge-plugin/ceo-loop-cancelgit clone --depth 1 https://github.com/nxtg-ai/forge-pluginWrote 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/commands/nxtg-ai/forge-plugin/ceo-loop-cancel)<a href="https://agentmods.dev/commands/nxtg-ai/forge-plugin/ceo-loop-cancel"><img src="https://agentmods.dev/badge/commands/nxtg-ai/forge-plugin/ceo-loop-cancel.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 | $0.00000 | $0.01022 |
| Opus 5 | $0.00000 | $0.00511 |
| Sonnet 5 | $0.00000 | $0.00204 |
| Haiku 4.5 | $0.00000 | $0.00102 |
Grade A, and why
ceo-loop-cancel 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 3d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/forge:ceo-loop-cancel
Gracefully stop the active CEO Decision Loop, write a final session summary with statistics, and preserve the complete decision journal for future sessions.
| Level | L1 Vibe Coder |
| Category | CEO Decision Loop |
| Syntax | /forge:ceo-loop-cancel |
What It Does
/forge:ceo-loop-cancel is the graceful exit from an active CEO-LOOP ORBIT cycle. It reads the current loop state, collects session statistics (iterations completed, decisions made, auto-approved count, escalated count, accuracy percentage, trust level), writes a final session summary to the progress file, sets the loop to inactive, and reports the results. Most importantly, it never deletes the decision journal -- all decisions from the session are preserved.
The command is idempotent and safe. If no loop is active, it reports that and exits. If a loop is running, it stops cleanly. Pending decisions that were not processed remain in .claude/ceo-decisions-pending.json for the next session. The next time you run /forge:ceo-loop, it picks up from the journal history.
Without this command, the only way to stop the loop would be to manually edit the state file or wait for the max-iterations or time-limit to expire. /forge:ceo-loop-cancel provides a clean, documented exit with full statistics.
Syntax & Options
/forge:ceo-loop-cancel
This command takes no arguments. It always cancels the active loop.
When to Use It
- Ending a governance session: When you have made enough decisions and want to return to normal work.
- Before switching context: Stop the loop before moving to a different project or task type.
- Emergency stop: If the loop is making decisions you disagree with, cancel it and review the journal.
To restart the loop after cancelling, run /forge:ceo-loop again. It starts a fresh session but retains the journal history.
Examples
Example 1: Standard Cancellation
/forge:ceo-loop-cancel
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.
- 3d ago First seen · 100 lines · 0 tokens per session scan A e9ab87d0591f
ceo-loop-cancel is a command published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,022 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.
Other commands, from other repositories
evidence
Export a signed compliance evidence package as JSON or PDF for regulatory handoff.
init-project
Configure the baseline for this specific project. Invokes the scout skill, then claude-automation-recommender, populates .claude/project.json, pre-creates lazy directories, re-renders swarm-worker.md from its template with any stack-specific skills appended, appends a §16 addendum to docs/init/seed.md, runs…
ai-act-incidents
Show real-world and research-demonstrated security incidents that map to a scanner dimension, EU AI Act article, or threat category. Surfaces OWASP LLM/ASI, NIST AI RMF, and MITRE ATLAS cross-references alongside published mitigations.
init-project-doctor
Detect and repair baseline drift — missing or invalid .claude/workflows.jsonl, schema violations, four-way Article IV / §18 mirror drift, and (advisory) shipped-tooling files placed outside .claude/ against the convention codified at seed.md §3. Interactive: presents each detected violation via AskUserQuestion and…
grant-commit
Grant consent for Claude to run git commit. Workflow-scoped when a workflow is active, else a time window. Required by the Git Commit Guard hook.
approve-direction
Record human approval of a workflow's direction (the intake + its acceptance criteria + the CO-A evidence). The Direction Approval Guard hook blocks Claude from ever writing approval tokens; this command is the only sanctioned path. Must be user-invoked. Replaces the retired /approve-spec gate (D3/CO-E gate-collapse)…