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 skills/superplan-md/superplan-plugin/superplan-verifynpx skills add superplan-md/superplan-plugin --skill superplan-verifygit clone --depth 1 https://github.com/superplan-md/superplan-pluginWhat 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 | $0.00033 | $0.00402 |
| Opus 5 | $0.00016 | $0.00201 |
| Sonnet 5 | $0.00007 | $0.00080 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
superplan-verify 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 2d 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.
What it actually says
Verification Before Completion
Overview
Do not claim success without evidence.
This is the generic discipline gate that runs before completion claims. It is not the same as Superplan's final AC review, but it feeds that review.
Gate Law
No claim of complete, fixed, passing, or ready for handoff without running the relevant proof first.
Hard Gate
Do not use confidence, code inspection, or stale output as a substitute for fresh verification evidence.
Trigger
Use when:
- the agent is about to say a task is complete, fixed, passing, or ready
- fresh evidence must be gathered from the current workspace harness
- output confidence is starting to outrun proof
Core Rules
- run the relevant checks before making success claims
- prefer the repo's trusted scripts, custom skills, browser flows, and QA routines
- if no existing trusted path proves the AC directly, derive the smallest credible verification loop that does
- map verification to the actual acceptance criteria
- distinguish strong proof from weak supporting evidence
- use static analysis only as a constrained fallback when stronger proof is unavailable or disproportionate
- surface stale, missing, or partial evidence honestly
- hand results cleanly to
superplan-reviewwhen tracked task completion is at stake
Forbidden Behavior
- saying "should be fixed" without running anything
- running checks that do not actually prove the acceptance criteria
- treating stale evidence as current proof
- using a Superplan-specific path when the repo already has a better trusted one
- treating static analysis as full proof for runtime or user-visible behavior when stronger proof is realistically available
Handoff
For tracked tasks, verification hands into superplan-review.
For non-tracked work, it still governs whether any success claim is honest.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 54 lines · 33 tokens per session scan A 6f3af5f5cbc2
superplan-verify is a skill published in the GitHub repository superplan-md/superplan-plugin (72 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 402 once invoked, about $0.0002 per session on Opus 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
setup
First-run experience for the harness. Three modes: Recommended (guided, 3 min), Full Tour (guided + skill walkthrough, 8 min), and Express (zero questions, 30 sec). Installs hooks first, detects stack, configures harness.json, runs a live demo on real code, and prints a reference card.
evolve
Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
research
Focused research investigations. Converts questions into structured findings with confidence levels and source citations. Single agent by default; with --parallel (or when the question decomposes into 3+ independent angles) it spawns scout agents whose findings are compressed into a unified brief. Does not make…
ascii-diagram
Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification.
triage
GitHub issue and PR investigator. Pulls open issues/PRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Use for investigating GitHub issues and reviewing PRs; do NOT use for general code review unrelated to…