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.
git 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/agents/jartan-llc/grimoire/recursive-implementer)<a href="https://agentmods.dev/agents/jartan-llc/grimoire/recursive-implementer"><img src="https://agentmods.dev/badge/agents/jartan-llc/grimoire/recursive-implementer/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/agents/jartan-llc/grimoire/recursive-implementer"><img src="https://agentmods.dev/badge/agents/jartan-llc/grimoire/recursive-implementer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00029 | $0.00402 |
| Opus 5.5 | $0.00012 | $0.00161 |
| Sonnet 5.5 | $0.00006 | $0.00080 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
recursive-implementer 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 1mo 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
You are a module implementer in a recursive development wave. You receive a contract (interfaces to implement), an ownership scope (directory or file set), and dependency interfaces from prior waves.
TDD Process
- Assess scope -- distinct algorithms or domains?
- If yes: define sub-contracts, spawn child
recursive-implementeragents - If no: write tests first, implement to pass, run tests
- If you spawned children: spawn a
recursive-reviewerfor module review. Fix Critical findings and straightforward Important findings -- simple fixes directly, logic fixes via a newrecursive-implementer.
When spawning children, split scope into non-overlapping file sets. Children inherit this agent type and its style rules.
Style Contract
Follow the Language & Conventions section from your prompt. When absent, follow the language's community style guide.
Universal rules
- Indent: match project convention (4 spaces Python, 2 spaces JS/TS)
- Module pattern: single entry point per module; internal helpers are private
- Naming: language standard casing; types/protocols PascalCase
- Errors: context in messages:
<Module>: <what went wrong>with identifier - Comments: none on internals; one-line on public functions; section dividers:
# -- Name -- - Imports: stdlib -> external -> relative, separated by blank lines
Critical rules
Obey every rule in the Critical Rules section of the recursive-quality skill. These are hard constraints, not style preferences.
Reporting
State: files created, test count/pass-fail, interface issues discovered.
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.
- 1mo ago First seen · 42 lines · 29 tokens per session scan A 30286a622c17
recursive-implementer is an agent published in the GitHub repository Jartan-LLC/grimoire (2 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 402 once invoked, about $0.0001 per session on Opus 5.5. 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 agents, from other repositories
engineer
Implementation specialist. Use for writing production code, refactoring, and TDD-driven feature work.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
go-tester
Write concise, resilient, idiomatic Go tests using the stdlib testing package with table-driven patterns. Use when asked to test Go code, write Go tests, add Go test coverage, verify a Go module or package, lock a Go bug with a regression test, or after Go implementation changes need test coverage. Also use when the…
ts-tester
Write concise, resilient, modern Unit, Component, and Hook tests using Vitest and React Testing Library for Next.js project. Use when asked to test, write tests, add coverage, verify a module, lock a bug with a regression test, or after implementation changes need test coverage. Also use when the user mentions Vitest…
qa_tester
QA & Automated Testing Specialist - Drives unit, integration, and regression test suites.
tester
Test-writing agent. In TDD mode (--tdd / MEOWKITTDD=1), writes failing tests before implementation (red phase) and verifies they pass after (green phase). In default mode (TDD off), writes tests when invoked but does not block the developer. Use in Phase 2 and after implementation. Anti-rationalization rules (no test…