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 Aiyo28/memento-os --skill grill-megit clone --depth 1 https://github.com/Aiyo28/memento-osWrote 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/aiyo28/memento-os/grill-me)<a href="https://agentmods.dev/skills/aiyo28/memento-os/grill-me"><img src="https://agentmods.dev/badge/skills/aiyo28/memento-os/grill-me/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/aiyo28/memento-os/grill-me"><img src="https://agentmods.dev/badge/skills/aiyo28/memento-os/grill-me.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 | $0.00078 | $0.00901 |
| Opus 5 | $0.00039 | $0.00451 |
| Sonnet 5 | $0.00016 | $0.00180 |
| Haiku 4.5 | $0.00008 | $0.00090 |
Grade A, and why
grill-me 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 12d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/grill-me
Interview relentlessly until every branch of the decision tree is walked and resolved. The goal is shared understanding — not critique for its own sake, but surfacing the gaps that would bite later.
Context Loading (Vault Retrieval Gate)
Before grilling, run the retrieval gate to surface prior decisions:
- Scan
_context.mdActive Reasoning Artifacts table for[D]entries matching the domain - Glob
Decisions/*{topic}*for full artifact files - If prior decision found → use as grilling context: "You decided X on {date}. Has the invalidation trigger fired?"
- Load domain-relevant vault knowledge:
- Technical → Glob
{vault_path}/Knowledge/AI*,Knowledge/MOC — *if exists - Business → Glob
{vault_path}/Knowledge/Business*
- Technical → Glob
- Use matched notes + prior decisions as grilling ammunition
Before You Start
- Read the plan/design the user is referring to (file, conversation context, or ask them to state it)
- If a codebase exists, explore it first — don't ask questions you could answer by reading code
Grilling Protocol
Work through these dimensions one at a time. For each, ask pointed questions, wait for answers, and probe deeper before moving on. Don't shotgun a list of 10 questions — go one branch at a time and resolve it.
1. Assumptions
What are you taking for granted? What must be true for this to work? Ask about each assumption and whether it's been validated.
2. Dependencies
What does this depend on? What depends on this? Walk the dependency chain and look for circular dependencies, bottlenecks, or single points of failure.
3. Edge Cases
What happens when inputs are unexpected? When scale changes? When the user does something you didn't plan for? When things fail halfway through?
4. Trade-offs
What did you give up to get this design? Are you aware of the cost? Would a different trade-off serve you better?
5. Alternatives
Why this approach and not the obvious alternatives? If the user can't articulate why, that's a gap.
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.
- 12d ago First seen · 82 lines · 78 tokens per session scan A bf6b718ddebe
grill-me is a skill published in the GitHub repository Aiyo28/memento-os (4 stars, last pushed 6d ago), licensed MIT. It adds 78 tokens to every session and 901 once invoked, about $0.0004 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
memory-to-skill
Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under…
pre-pr
Prepare a Honcho change for a pull request to plastic-labs/honcho. Invoke before opening a PR, when drafting a PR body, when asked if a branch is PR-ready, or when filling the pull request template. Checks the linked issue, required tests and docs, then writes Description / Proofs / Fixes.
lorekeeper-dev-self-review
Mandatory Reflexion self-review loop for all Lorekeeper devs before pushing or opening PRs. Actor → Evaluator → Reflector cycle (max 3 iterations). Every dev must run this before git push.
requesting-code-review
Pre-commit review: security scan, quality gates, auto-fix.
lorekeeper-code-reviewer
Lorekeeper-specific BLOCKER patterns, severity tiers, and review checklist — used when reviewing any PR touching src/lorekeeper/.
triage-aging-prs
Drive an aging pull-request backlog to zero. Inventories every open PR, finds the STRUCTURAL blockers first (a required check that can never run, a reviewer that never fires, chronically red CI), triages every unresolved review thread in parallel and VERIFIES each finding against the code before fixing it, then merges…