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/janeksm/mcp-digger/devnpx skills add janeksm/mcp-digger --skill devgit clone --depth 1 https://github.com/janeksm/mcp-diggerWhat 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 | $0.00020 | $0.00854 |
| Opus 5 | $0.00010 | $0.00427 |
| Sonnet 5 | $0.00004 | $0.00171 |
| Haiku 4.5 | $0.00002 | $0.00085 |
Grade A, and why
dev 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 yesterday.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Cycle
Full TDD development cycle from planning through verified implementation. Reads/writes CMCM knowledge files (decisions, patterns, handoff).
Task: $ARGUMENTS
Instructions
Phase 1 — Dual-Source Plan + Skeptic Review
-
Resolve task context.
- If
$ARGUMENTSis a step number: readTODO.mdfor task details (description, rationale, files). - If
$ARGUMENTSis a description: use it directly. - Read CMCM files (if they exist, skip silently if missing):
HANDOFF.md— if present, display session continuity before proceeding (covers the case where/loadwas skipped)DECISIONS.md— prior technical decisions (stays in context for planning)PATTERNS.md— established code patterns (stays in context for planning)CC.md— Node.js / TypeScript clean code rules (stays in context for planning and implementation)
- If
-
Run /plan-x. Invoke the plan-x skill with the task description. This handles:
- Launching Codex planning in background
- Interactive plan mode with the user
- Merging Codex additions into the approved plan
- Skeptic review via /plan-review
DECISIONS.md and PATTERNS.md are already in context from step 1. When formulating the plan:
- Reference relevant decisions — the plan must not contradict prior decisions without explicitly revisiting them.
- Reference applicable patterns — the plan should reuse established patterns rather than inventing new approaches.
-
Wait for /plan-x to complete (plan approved, reviewed, and finalized) before continuing.
Phase 2 — Record Decisions & Session State
-
Log rejected alternatives — MANDATORY CHECK. After the plan is approved, explicitly review the planning discussion and ask: "Were any alternative approaches considered and rejected?"
- If YES → append to
DECISIONS.md:## YYYY-MM-DD — short title Chose X over Y. Why: reasoning from the plan discussion - If NO (straightforward, no real alternatives) → skip, but confirm in output:
DECISIONS.md: no new entries (no alternatives considered)
- If YES → append to
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.
- yesterday First seen · 81 lines · 20 tokens per session scan A 3603563ed34a
dev is a skill published in the GitHub repository janeksm/mcp-digger (0 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 854 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
widget-creator
Step-by-step guide for creating new widgets in the Hex1b TUI library. Use when implementing new widgets from scratch, including widget records, nodes, extension methods, theming, reconciliation, and tests.
aspire
Orchestrates Aspire distributed applications using the Aspire CLI for running, debugging, and managing distributed apps. USE FOR: aspire start, aspire stop, start aspire app, aspire describe, list aspire integrations, debug aspire issues, view aspire logs, add aspire resource, aspire dashboard, update aspire apphost.…
webui-design
このドキュメントは moorestech Web UI の見た目・構造のホワイトリストである。.
pr-independent-review
実装セッションと完全に独立したセッションでPRをレビューする手動発火スキル。PR URLまたは番号を受け取り、 レビュー専用worktreeにcheckoutして moores-code-review（report-only）＋新規性ゲートL1を実行し、 実コード抜粋入りのインフォグラフィックHTMLダイジェスト（verdict/裁定カード/suppressed）と シャドー台帳を出力する。ダイジェストの閲覧は裁定サイト（https://review.moores.tech/pr/ ）が担う。 実装セッションの自己申告contextは一切受け取らない。…
subagent-driven-development
現在のセッションで、独立したタスクからなる実装計画を実行する際に使用する.
moores-code-review
Skill "moores-code-review" from moorestech/moorestech, covering moores-code-review, workflow実行（既定・2026-08-20）, 回収時の検死（本体・毎回必須）, step 0: 実行ディレクトリ $rundir を作る and step 1: レビュー対象と4カテゴリcontextを確定する.