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 6ixGODD/mine --skill mine-plan-reviewgit clone --depth 1 https://github.com/6ixGODD/mineWrote 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/6ixgodd/mine/mine-plan-review)<a href="https://agentmods.dev/skills/6ixgodd/mine/mine-plan-review"><img src="https://agentmods.dev/badge/skills/6ixgodd/mine/mine-plan-review.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00100 | $0.06965 |
| Opus 5 | $0.00050 | $0.03483 |
| Sonnet 5 | $0.00020 | $0.01393 |
| Haiku 4.5 | $0.00010 | $0.00696 |
Grade A, and why
mine-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 4d 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 — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MINE Plan Review
MINE Is Not Everyone's. Act as an independent acceptance reviewer, not as the implementing agent's advocate. Try to falsify the implementation's claims. Accept only when the plan's actual contract is demonstrated end to end.
Integration: MCP tools and CLI fallback
mine-plan-review queries and transitions plan state through two paths, in
this order of preference:
- MCP tools (preferred) - when the current Agent runtime exposes the
MINE MCP server (
mine mcp serve), call the typed MCP tools. They return the same DTOs as the JSON CLI and never touch the execution-graph files. - JSON CLI (deterministic fallback) - when MCP is unavailable, call
mine --format jsoncommands. Never parse human output.
Never invent an MCP tool, CLI command, flag, JSON field, or lifecycle
transition that the current binary does not expose. Never edit
docs/plan/execution-graph.toml or docs/plan/execution-graph.md directly.
The accepted MCP tools mine-plan-review may use:
mine_graph_status(no arguments) - read the current revision.mine_plan_show(id) - read the target node, its predecessors, and status.mine_plan_accept(id,review) - transitionIMPLEMENTED->ACCEPTEDand record the review report path.mine_plan_reject(id,reason,review_report,compensating_plan) - evidence-bound transition fromIMPLEMENTEDor an objectively infeasibleIN_PROGRESSPlan toREJECTED.mine_plan_withdraw(id,reason) - owner-authorized retirement of an unstarted (DRAFT/BLOCKED/READY) registration into terminalWITHDRAWN(ADR-0012). Withdrawn nodes are retired: they never block workspace closure and are never revived.mine_graph_validate(no arguments) - validate the graph after transitions.mine_design_validate(no arguments) - confirm design references.
Operations mine-plan-review needs that are intentionally CLI-only (no
MCP tool exposes them, because they rewire downstream dependencies outside
the single-node accept/reject path):
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.
- 4d ago Changed · +6 lines c2dbd44a4e20
- 8d ago First seen · 367 lines · 100 tokens per session scan A fd6e8861c681
mine-plan-review is a skill published in the GitHub repository 6ixGODD/mine (17 stars, last pushed 3d ago), licensed MIT. It adds 100 tokens to every session and 6,965 once invoked, about $0.0005 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
refactor-engineer
Use when the user requests a behavior-preserving code refactor, cleanup, extraction, consolidation, or architectural simplification. Map all references and contracts before editing, keep the change scoped, and prove behavior with focused tests and type checks.
vibe-quality-loop
Enforces the Implement→Review→Test→Fix→Loop cycle until work is clean. Use after any non-trivial implementation to prevent "good enough" exits.
pr-test-analyzer
Use when reviewing a PR to evaluate test coverage quality and identify critical gaps for new or changed functionality.
dev-cli-tooling-workflow
Use to design, implement, review, or test CLI tools, flags, config precedence, terminal UX, errors, and docs.
adversarial-verification
Use when verifying implementation work and the failure mode is superficial approval, code-reading in place of execution, or over-trusting a passing test suite without trying to break the change.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.