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.
git 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/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/commands/nxtg-ai/forge-plugin/ceo-loop-cancel"><img src="https://agentmods.dev/badge/commands/nxtg-ai/forge-plugin/ceo-loop-cancel.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00055 | $0.01047 |
| Opus 5.5 | $0.00022 | $0.00419 |
| Sonnet 5.5 | $0.00011 | $0.00209 |
| Haiku 4.5 | $0.00006 | $0.00105 |
Grade B, and why
ceo-loop-cancel scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/ceo-loop-state.json 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/nxtg-forge:ceo-loop-cancel — Cancel CEO Decision Loop
Graceful exit from the CEO-LOOP ORBIT cycle.
Step 1 — Check current state
cat .claude/ceo-loop-state.json 2>/dev/null
If no state file exists or active: false: report "No CEO-LOOP is currently active" and exit.
Step 2 — Collect session statistics
Read stats for the final summary:
# Get state values
ITERATION=$(jq -r '.iteration // 0' .claude/ceo-loop-state.json 2>/dev/null)
STARTED=$(jq -r '.started_at // "unknown"' .claude/ceo-loop-state.json 2>/dev/null)
CORRECT=$(jq -r '.correct_decisions // 0' .claude/ceo-loop-state.json 2>/dev/null)
INCORRECT=$(jq -r '.incorrect_decisions // 0' .claude/ceo-loop-state.json 2>/dev/null)
TRUST=$(jq -r '.trust_level // "standard"' .claude/ceo-loop-state.json 2>/dev/null)
# Count decisions in journal
TOTAL_DECISIONS=$(wc -l < .claude/ceo-loop-decisions.jsonl 2>/dev/null || echo 0)
AUTO_APPROVED=$(grep -c '"tier":"auto_approve"' .claude/ceo-loop-decisions.jsonl 2>/dev/null || echo 0)
ESCALATED=$(grep -c '"tier":"escalate"' .claude/ceo-loop-decisions.jsonl 2>/dev/null || echo 0)
# Count pending items remaining
PENDING=$(jq 'length' .claude/ceo-decisions-pending.json 2>/dev/null || echo 0)
Step 3 — Write final session summary to progress file
Append a final section to .claude/ceo-loop-progress.md:
---
## SESSION END — Cancelled by user
**Cancelled at**: <ISO timestamp>
**Started**: <started_at>
**Completed iterations**: <N>
### Final Session Statistics
| Metric | Value |
|--------|-------|
| Total decisions | <TOTAL_DECISIONS> |
| Auto-approved (trivial) | <AUTO_APPROVED> |
| Escalated to human | <ESCALATED> |
| Deep decisions | <TOTAL - AUTO - ESCALATED> |
| Correct (retrograde confirmed) | <CORRECT> |
| Incorrect (retrograde failed) | <INCORRECT> |
| Final accuracy | <pct>% |
| Trust level at exit | <TRUST> |
### Queue at cancellation
- Remaining pending decisions: <PENDING>
- Decision journal preserved at: `.claude/ceo-loop-decisions.jsonl`
Resume next session with: `/nxtg-forge:ceo-loop` (will pick up from journal)
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.
- 12d ago Changed 525eede08d04
- 1mo ago Changed · +7 lines · +55 tokens per session scan A → B 88f8378833d7
- 1mo 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 (6 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 1,047 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
paul:help
Show available PAUL commands and usage guide.
paul:verify
Guide manual user acceptance testing of recently built features.
deep-audit.skeleton
Description: This section is populated by Bootstrap with manifest data. Required manifest fields: project.description, stack.primary, project.structure, project.subprojects, stack.orm, stack.authmethod Example output.
mutate
Run mutation testing to verify test quality. Builds a custom mutation tool or uses an existing framework, runs mutations, and reports the mutation score with surviving mutants.
hatch3r-refactor-plan
Plan a refactoring or migration effort -- spawn parallel researchers, produce refactoring spec, ADR(s), and phased todo.md entries for board-fill.
test-coverage
Analyze test coverage and identify the highest-value gaps to fill.