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 Team-Deepiri/deepiri-axiom --skill plan-arbitergit clone --depth 1 https://github.com/Team-Deepiri/deepiri-axiomWrote 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/team-deepiri/deepiri-axiom/plan-arbiter)<a href="https://agentmods.dev/skills/team-deepiri/deepiri-axiom/plan-arbiter"><img src="https://agentmods.dev/badge/skills/team-deepiri/deepiri-axiom/plan-arbiter/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/team-deepiri/deepiri-axiom/plan-arbiter"><img src="https://agentmods.dev/badge/skills/team-deepiri/deepiri-axiom/plan-arbiter.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 | $0.00044 | $0.00612 |
| Opus 5.5 | $0.00018 | $0.00245 |
| Sonnet 5.5 | $0.00009 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
plan-arbiter 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 11d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan arbiter
Turn competing plans into one executable direction. Preserve best ideas; reject weak assumptions; avoid blended mush.
Source: BuilderIO/skills (plan-arbiter). MIT.
Planning is read-only unless the user explicitly asks to implement after the decision.
Workflow
- Collect source plans
- Normalize into comparable claims
- Cross-review against each other and the real codebase/task
- Adopt, hybridize, or send back for revision
- One execution handoff with verification gates and rejected alternatives
Collect
Accept pasted text, files, transcripts, PRs, comments, or chat history. Resolve originals when possible. If still writing and user asked to wait, monitor until done/blocked. Mark unresolved sources as risk.
Normalize (per plan)
- Objective and scope
- Assumptions and open questions
- Proposed files/modules/APIs/data/UI/workflows
- Implementation sequence
- Validation strategy
- Rollback / migration concerns
- Cost, complexity, executor fit
Prefer concrete, grounded, honest plans over verbosity.
Cross-review
- Satisfies the actual request?
- Claims match repo/docs/tests when available?
- Hidden deps, missing tests, risky sequencing, vague steps, excess scope?
- Complementary strengths across plans?
- Separate plan quality from which model should execute
Use subagents for large plans or separate technical vs product passes.
Decide
- Adopt — one plan mostly as written
- Hybrid — combine specific pieces
- Revise first — both miss a key constraint
Tie-break: (1) correctness/fit (2) grounding (3) simpler first step that doesn't block the future (4) better validation/rollback (5) lower execution cost once quality is ok
Handoff memo
Decision
- Adopt Plan A / Hybrid / Revise first.
Why
- Deciding evidence and tradeoffs.
Execution Plan
- Ordered steps with files or surfaces to touch.
Borrowed From Other Plans
- Useful pieces kept from non-winning plans.
Rejected
- Ideas intentionally not taking, with reasons.
Verification
- Tests, checks, review, or deploy gates needed.
Executor Recommendation
- Which agent/model should implement and why.
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.
- 11d ago First seen · 91 lines · 44 tokens per session scan A cbeb1be145c7
plan-arbiter is a skill published in the GitHub repository Team-Deepiri/deepiri-axiom (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 612 once invoked, about $0.0002 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 2026-10-26.
plan-arbiter compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| plan-arbiterTeam-Deepiri/deepiri-axiom | Skill | 2 | yesterday | Apache-2.0 | A | 44 | Claude Code |
| autoreviewopenclaw/clawhub | Skill | 9.5k | yesterday | MIT | A | 17 | Claude Code, Codex |
| agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills | Skill | 2.2k | 6d ago | MIT | A | 115 | Claude Code, Codex |
| omh-code-reviewrlaope/oh-my-hermes | Skill | 5.2k | yesterday | MIT | A | 48 | Claude Code, Codex |
| revdiff-planumputun/revdiff | Skill | 945 | 2d ago | MIT | A | 84 | Claude Code |
| explore-unknownsdzhng/skills | Skill | 1.4k | 2d ago | MIT | A | 162 | Claude Code, Codex |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | 4d ago | MIT | A | 70 | Claude Code |