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 pantheon-org/tekhne --skill plan-reviewgit clone --depth 1 https://github.com/pantheon-org/tekhneWrote 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/pantheon-org/tekhne/plan-review)<a href="https://agentmods.dev/skills/pantheon-org/tekhne/plan-review"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/plan-review/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/pantheon-org/tekhne/plan-review"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/plan-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 218 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 384 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00176 | $0.05985 |
| Opus 5 | $0.00088 | $0.02993 |
| Sonnet 5 | $0.00035 | $0.01197 |
| Haiku 4.5 | $0.00018 | $0.00598 |
Grade A, and why
plan-review 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 9d 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 — 496 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Review -- 3-Agent Multi-Perspective Audit
Review .context/plans/ files through 3 independent lenses: Technical,
Strategic, and Risk. Each reviewer is a separate subagent with a unique
prompt and perspective. The main agent collates results into a consolidated report.
This catches what a single reviewer normalises -- each subagent brings a fresh set of assumptions and focus areas.
Prerequisites
- A
.context/plans/*.mdfile exists to review (or a glob selecting multiple) - The plan has standard YAML frontmatter (
title,type,status,date) - Your environment supports spawning
generalandexploresubagent types
Quick Start
# No CLI commands -- this is an agent workflow skill.
# Load the skill, then say: "review the plan at .context/plans/<name>.md"
When to Use
- A
.context/plans/*.mdfile needs an independent multi-perspective review before implementation - A draft plan needs validation before marking it
READY - Multiple plans exist in the same domain and need prioritisation
- A stale plan needs a freshness check against current project state
- The user explicitly asks for a plan audit
When NOT to Use
- For one-off notes, scratch files, or non-plan documents -- use
session-reflectioninstead - For plans outside
.context/plans/-- the reviewer prompts assume.context/frontmatter conventions - When the plan is trivially small (1 paragraph, no steps) -- the overhead of 3 subagents is not justified
- When the user explicitly asks for a quick opinion, not a full audit
Mindset
- Three independent reviewers catch what a single reviewer normalises. The value is in the divergence between their findings, not in consensus.
- Model diversity is the strongest lever for perspective diversity. PREFER routing each reviewer to a different model UNLESS the environment genuinely offers no routing (see Advanced: Model Routing Configuration).
- A plan review is a service to the plan author, not a judgement. Findings should be actionable, not critical.
- Structural validation is a prerequisite, not the goal. The frontmatter check exists to keep the plan visible in the index, but the real value is the implementation architecture and risk analysis from the 3 reviewers.
- If a review reveals a critical issue, the right outcome is to improve the plan, not to reject it.
- BY DEFAULT, classify every critical/moderate finding as Editorial or Decision (Step 10) before calling the review finished. TYPICALLY most structural gaps are Editorial (one clearly correct fix); RECOMMENDED to reserve the Decision bucket, and its interview, for genuine tradeoffs only -- AVOID interviewing the user on something that was never actually in question.
What ships with it
22 files 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.
- assets/schemas/model-selection.schema.json 1.3 KB
- assets/schemas/review-report.schema.json 8.3 KB
- assets/templates/model-selection.yaml 962 B
- assets/templates/review-report.yaml 2.5 KB
- evals/instructions.json 4.0 KB
- evals/scenario-01/capability.txt 153 B
- evals/scenario-01/criteria.json 2.0 KB
- evals/scenario-01/task.md 2.1 KB
- evals/scenario-02/capability.txt 186 B
- evals/scenario-02/criteria.json 2.1 KB
- evals/scenario-02/task.md 2.8 KB
- evals/scenario-03/capability.txt 150 B
- evals/scenario-03/criteria.json 2.1 KB
- evals/scenario-03/task.md 1.8 KB
- evals/scenario-04/capability.txt 167 B
- evals/scenario-04/criteria.json 2.0 KB
- evals/scenario-04/task.md 2.0 KB
- evals/summary.json 155 B
- references/model-routing.md 5.7 KB
- references/structural-inference.md 4.2 KB
- scripts/validate-model-selection.sh 2.0 KB runs code
- scripts/validate-review-report.sh 2.1 KB runs code
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.
- 9d ago First seen · 496 lines · 176 tokens per session scan A 924b7c10e3fc
plan-review is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed yesterday), licensed MIT. It adds 176 tokens to every session and 5,985 once invoked, about $0.0009 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 2026-09-03.
Other skills, from other repositories
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
atlas-obscura
Search Atlas Obscura for weird, wonderful, and hidden gem places near any destination. Find the interesting stuff, not boring plaques. Search by coordinates, get full details with descriptions and images.
agent-code-generator
Generates Agent definitions (.md files) based on user intent and standard templates.
cf-validate
A validator for 1C configuration source files. It checks the XML structure and the files and objects that make up a 1C business-application configuration.