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/jartan-llc/grimoire/recursive-implementnpx skills add Jartan-LLC/grimoire --skill recursive-implementgit clone --depth 1 https://github.com/Jartan-LLC/grimoireWrote 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/jartan-llc/grimoire/recursive-implement)<a href="https://agentmods.dev/skills/jartan-llc/grimoire/recursive-implement"><img src="https://agentmods.dev/badge/skills/jartan-llc/grimoire/recursive-implement.svg" alt="Measured on agentmods" 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 | $0.00015 | $0.00332 |
| Opus 5 | $0.00008 | $0.00166 |
| Sonnet 5 | $0.00003 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
recursive-implement 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 3d 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
Recursive Implement
Build a project (or feature) using waves of parallel nested subagents with TDD at every level.
Process
1. Gather Context
Collect everything the orchestrator needs into a single prompt:
- From the user's request: the project description, issue number, or plan file path
- If issue number: fetch the issue body with
gh issue view <number>and include it - From conversation: if the user discussed requirements, architecture decisions, constraints, or preferences in this session, summarize the relevant parts
- From existing project: if working in an existing codebase, note the language, test framework, key conventions, and any relevant file paths
2. Launch Orchestrator
Spawn a recursive-orchestrator. The prompt should contain:
[Project description or plan file path]
[Conversation context if any -- requirements, constraints, decisions made]
[Existing project context if any -- language, conventions, key files]
Working directory: [cwd]
3. Report Results
Relay the orchestrator's final report to the user.
Failure Recovery
If the orchestrator reports a failure, present the context to the user. On re-run:
- The wave plan persists in
.claude/workspace/-- pass the file path to skip re-planning - Completed source files and tests remain on disk -- the orchestrator can build on them
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.
- 3d ago First seen · 46 lines · 15 tokens per session scan A 29f9f1d0f61c
recursive-implement is a skill published in the GitHub repository Jartan-LLC/grimoire (2 stars, last pushed 16d ago), licensed MIT. It adds 15 tokens to every session and 332 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
request-to-spec-issues
Use after a grill-change session is complete to turn the agreement record into an intent-first spec candidate and vertical TDD-ready issue briefs.
tdd-change
Use when changing behavior where a focused failing test or golden fixture must prove RED before implementation and GREEN after the minimal fix.
loop-sdd-cycle
Use to run a bounded spec, tests, implementation, and verify cycle that stops on green, on no diff, or on a repeated identical failure.
tdd-loop
Implement a known feature, behavior change, or diagnosed bug with a red-green-refactor loop. Use when the user asks to add, build, implement, or fix behavior and automated tests exist or should exist. For an unknown failure cause use debug-protocol first; for model, prompt, RAG, or agent quality use…
tdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…