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 tmusser/ai-engineering-skills --skill grill-with-docs-litegit clone --depth 1 https://github.com/tmusser/ai-engineering-skillsWrote 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/tmusser/ai-engineering-skills/grill-with-docs-lite)<a href="https://agentmods.dev/skills/tmusser/ai-engineering-skills/grill-with-docs-lite"><img src="https://agentmods.dev/badge/skills/tmusser/ai-engineering-skills/grill-with-docs-lite/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/tmusser/ai-engineering-skills/grill-with-docs-lite"><img src="https://agentmods.dev/badge/skills/tmusser/ai-engineering-skills/grill-with-docs-lite.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 | $0.00047 | $0.01699 |
| Opus 5 | $0.00023 | $0.00849 |
| Sonnet 5 | $0.00009 | $0.00340 |
| Haiku 4.5 | $0.00005 | $0.00170 |
Grade A, and why
grill-with-docs-lite 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 11d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grill With Docs Lite
Purpose
Prepare trustworthy inputs for mini-spec before SPEC.md exists.
Turn a fuzzy but bounded AI-engineering request plus relevant docs/repo evidence into a compact PRE-SPEC ASSEMBLY packet. The packet should expose the source-backed facts, authority boundaries, contradictions, decisions, safe assumptions, verification anchors, and likely failure mode that mini-spec needs to assemble an auditable contract.
This is a pre-spec evidence-grooming gate, not a requirements author and not a domain-modeling workflow. It must not silently promote guesses, implementation details, or source silence into contract language.
PRE-SPEC ASSEMBLY replaces the older CLARIFICATION DELTA shape while preserving the same bounded pre-spec role.
When to use
Use when the task is probably small enough for mini-spec, but the request is still conversationally fuzzy or relevant docs/code may change the objective, acceptance boundary, compatibility surface, or proof target.
Skip it when the request is already crisp enough to write a bounded spec directly.
Use a fuller domain-model or architecture workflow instead when the work requires canonical vocabulary, multiple hard-to-reverse architectural decisions, cross-context modeling, or an open-ended decision tree.
Inputs
- User request
- Existing notes or docs
- Relevant repo files
CONTEXT.mdif present
Evidence classes
Every unresolved or decision-relevant item must stay visibly classified until mini-spec assembles the contract:
FACT— supported by a source; include the file/path, symbol, test, artifact, URL, or other locator.DECISION— requires an explicit user/product choice before it can become contract language.ASSUMPTION— a reversible working default that does not silently alter public behavior, schemas, security, permissions, data semantics, or compatibility.UNKNOWN— missing evidence that blocks safe specification or must remain explicitly unresolved.
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.
- 11d ago First seen · 190 lines · 47 tokens per session scan A 7ff53b8dfcea
grill-with-docs-lite is a skill published in the GitHub repository tmusser/ai-engineering-skills (4 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 1,699 once invoked, about $0.0002 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
awsl
Run Claude Code JavaScript Workflows through the awsl compatibility runtime. Use when an agent's current task or loaded Skill requires dispatching a Claude Code Workflow but the host cannot execute that Workflow natively, or when awsl workflow inspection, durable run state, resume, or provider diagnostics are needed.
dwi-all-in-one
Apply the relevant Dwi lenses together when several observed workflow problems co-occur. Select only the lenses the task needs, preserve a silent fast path for clear reversible work, and keep authority and evidence explicit. Prefer a focused module when one issue dominates.
dwi-arc
Structure genuinely multi-agent coding work into bounded cells with one writer per scope, explicit integration, and independent review. Use when several disjoint workstreams justify coordination. Do not use for small tasks, overlapping writers, speculative agent fleets, or process artifacts without demonstrated value.
dwi-bridge
Coordinate bounded work between native Claude and Codex workflows with explicit authority, scope, and evidence. Use for read-only consultation or explicitly authorized execution delegation. Do not create a new connector, share secrets, treat messages as authorization, or allow recursive delegation.
dwi-budget
Set and report practical token, context, time, tool-call, and coordination boundaries for coding-agent work. Use when resource use is unclear or needs a checkpoint. Do not invent measurements, monetary savings, cache benefit, or precision that the harness does not expose.
dwi-evidence
Label coding-agent claims by evidence status, preserve provenance and failures, and separate static, runtime, and human proof. Use before completion, comparison, promotion, or handoff. Do not upgrade observations into guarantees or fabricate missing measurements and approvals.