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/AltimateAI/claude-consensusWrote 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/altimateai/claude-consensus/plan-review)<a href="https://agentmods.dev/commands/altimateai/claude-consensus/plan-review"><img src="https://agentmods.dev/badge/commands/altimateai/claude-consensus/plan-review.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 | $0.00019 | $0.06581 |
| Opus 5 | $0.00010 | $0.03291 |
| Sonnet 5 | $0.00004 | $0.01316 |
| Haiku 4.5 | $0.00002 | $0.00658 |
Grade B, and why
plan-review scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
[ -f ~/.claude/.env ] && export OPENROUTER_API_KEY=$(grep '^OPENROUTER_API_KEY=' ~/.claude/.env | cut -d= -f2- | tr -d '"') How it starts
The opening of the file, as written. The whole thing — 515 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Model Plan Review
Get independent implementation plans from multiple AI models (Claude + configured external models), compare them, and converge on the strongest plan through structured synthesis and approval rounds.
Compaction Resilience
This is a long-running command. Context compaction may erase in-memory state mid-run.
- Check resume: Glob
data/scratch/active-progress-consensus-plan-review-*.md— find any with StatusIN_PROGRESSand < 24h old. If found, read its SESSION_DIR and skip to first unchecked goal. If Status isCOMPLETEDorFAILED, ignore it. - Write progress: After creating SESSION_DIR, create a unique progress file:
data/scratch/active-progress-consensus-plan-review-{SESSION_ID}.md(where SESSION_ID is the random suffix from SESSION_DIR, e.g.X4f2kL) - Mark done: Set Status to
COMPLETEDat end of successful run, orFAILEDon abort - Save incrementally: Write/append to
$SESSION_DIRfiles after each phase, not at the end
Goals Template
# consensus:plan-review — {TASK}
Started: [timestamp]
Status: IN_PROGRESS
Command: consensus:plan-review
SESSION_DIR: {SESSION_DIR path}
TTL: 24h
## Goals
- [ ] Phase 1 — Setup: load config, write task prompt, copy plan file if needed, create team
- [ ] Phase 2 — Spawn planners: launch teammate agents + write Claude's plan
- [ ] Phase 3 — Collect plans: wait for all models to send their plans
- [ ] Phase 4 — Analyze & compare: build comparison table, identify consensus approach
- [ ] Phase 5 — Synthesize: draft unified implementation plan
- [ ] Phase 6 — Convergence: send draft to all models, collect APPROVE/CHANGES NEEDED
- [ ] Phase 7 — Write final plan with attribution table, cleanup team
## Progress
- [HH:MM] Starting execution...
Checkpoints
- After Phase 2: Claude's plan written to
$SESSION_DIR/claude.md - After Phase 3: All model plans on disk at
$SESSION_DIR/{model.id}.md - After Phase 5: Draft plan at
$SESSION_DIR/draft.md - After Phase 6: Convergence responses at
$SESSION_DIR/{model.id}-convergence.md
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.
- 6d ago First seen · 515 lines · 19 tokens per session scan B afaa8f21c6e5
plan-review is a command published in the GitHub repository AltimateAI/claude-consensus (32 stars, last pushed 12d ago), licensed MIT. It adds 19 tokens to every session and 6,581 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other commands, from other repositories
save
Save current work state for next session. Creates/updates .planning/ files (CHECKPOINT.md, STATE.md, settings.json) so Heimdall resumes with full context. NOT a rewind — saves forward progress. Run before closing a session or at any milestone.
maintain
Run automated maintenance — seeker finds bugs from pod logs and raises GitHub issues, fixer picks them up and creates PRs. Can run as a one-shot or scheduled via /schedule.
create-skill
Scaffold a new scaffolding-compatible skill: an interactive flow that creates skills/ /SKILL.md from the canonical template, composes a TRIGGER/SKIP description, and validates the result.
autonomy
Set Heimdall autonomy (1=Guided, 2=Checkpoint, 3=Full Auto) — how much the agent does before asking. Use with a number, +/- to cycle, or no argument to show current.
init-rules
Scaffold opt-in path-scoped nested CLAUDE.md rule files into the project to lazy-load per-area conventions while keeping routing always-loaded.
level
Deprecated alias for /hmd:autonomy. Sets Heimdall autonomy (1=Guided, 2=Checkpoint, 3=Full Auto). Still works; prints a one-line rename notice.