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 Jartan-LLC/grimoire --skill recursive-qualitygit 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-quality)<a href="https://agentmods.dev/skills/jartan-llc/grimoire/recursive-quality"><img src="https://agentmods.dev/badge/skills/jartan-llc/grimoire/recursive-quality/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/jartan-llc/grimoire/recursive-quality"><img src="https://agentmods.dev/badge/skills/jartan-llc/grimoire/recursive-quality.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 | $0.00018 | $0.00890 |
| Opus 5.5 | $0.00007 | $0.00356 |
| Sonnet 5.5 | $0.00004 | $0.00178 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
recursive-quality 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recursive Quality
Contract Richness
Wave 0 contracts set the ceiling. Thin contracts -> thin implementations.
Completeness
- Enumerate all operations, not just common ones
- Enums for closed sets (prevents string-typing drift)
- Error types alongside success types (
Record | ParseError) - Custom exception hierarchy -- base + subtypes per failure domain
Flexibility
- Batch interfaces (
list[Spec]) over single-item - Injectable I/O (write callables, output streams) for testability
- Union return types for expected failures; exceptions for unexpected
Modularity
- Protocols/interfaces for DI -- not concrete dependencies
- Factories/registries for runtime selection
- Structured return types (
RunResult) over bare values
Typing boundaries
- Untyped/dynamic values (
Any,object) are acceptable at input boundaries -- parsed records, CLI args, external data where the shape is genuinely unknown - All internal result types (aggregation results, pipeline outputs, structured returns) must be fully typed -- the shape is known at design time
- Contracts file contains: protocols, dataclasses, enums, type aliases, constants. No callable stubs.
Critical Rules
These are never judgment calls. Implementers must not produce code that violates them. Reviewers must flag violations as Critical.
- Typed returns. No untyped/dynamic returns (
Any,object,interface{}) on public functions or protocol methods. Use the specific type or union. - Structured returns. No unstructured collection returns where contracts define or should define a structured type.
- No absolute paths. No hardcoded absolute paths in source or tests. Use the language's path library with relative paths.
- Logging, not stderr. Library code uses the language's logging framework with named loggers. Never write directly to stderr. Entry points configure level/format.
- Typed protocol signatures. Protocol/interface method parameters and returns must be fully typed. Untyped signatures cascade to every downstream module.
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 · 71 lines · 18 tokens per session scan A d1aaac8720f8
recursive-quality is a skill published in the GitHub repository Jartan-LLC/grimoire (2 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 890 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 2026-09-08.
Other skills, from other repositories
tastemaker
Generate genuinely beautiful, on-brand UI instead of generic "AI slop" — use whenever the user asks to build, design, style, or improve a UI, landing page, dashboard, app screen, or component, whenever a PRD/spec needs a design pass before implementation, whenever the user pastes reference images/Pinterest/Dribbble…
fde
Keeps the engagement record for client work. Use when they name a client or stakeholder. Use when they debrief a meeting or paste notes. Use when they ask what was agreed. Use when they run a POC, change the client's codebase, prove it on their staging, go live, or need evals before a model acts. Use when they prep a…
board-memo
Draft a board or executive summary of an engagement using outcomes, risks and investment decisions. Use when the sponsor needs to brief senior leadership.
brief
Clarify a new customer brief, desired outcome, constraints and evidence gaps. Use for kickoff or a first meeting; do not repeat discovery already supplied.
business-case
Develop a business case for an initiative using costs, benefits, risks and evidence. Use when a sponsor needs budget or timeline justification.
earn-trust
Plan how to earn customer trust and appropriate access. Use when credibility, permissions or AI policy constrain the engagement.