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 me-cedric/agent-compass --skill grillgit clone --depth 1 https://github.com/me-cedric/agent-compassWrote 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/me-cedric/agent-compass/grill)<a href="https://agentmods.dev/skills/me-cedric/agent-compass/grill"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/grill/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/me-cedric/agent-compass/grill"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/grill.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 | $0.00046 | $0.00764 |
| Opus 5.5 | $0.00018 | $0.00306 |
| Sonnet 5.5 | $0.00009 | $0.00153 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
grill 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 10d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
grill
Loop
- If the upstream skill
grill-meorgrillingis installed (source idmattpocock), follow its loop. Else use steps 2 to 5. To install it, addmattpococktoupstreamin.agents/compass.json, then runac sync. - Read the plan,
{{OPENSPEC_DIR}}and the code that the plan touches. Answer from them first. - Ask one question at a time. Give your recommended answer with each question.
- Ask the question that unblocks the most other questions first.
- Stop when no open question blocks the plan, or when the user says stop.
Harvest
Also scan {{OPENSPEC_DIR}} for findings:
- A
[NEEDS CLARIFICATION]marker. - A
## Clarificationssession. Each- Q: <question> → A: <answer>line is one finding. - Hedged prose such as "TBD", "to be confirmed", "we assume", "subject to". Match the language of the specs.
- An unstated premise behind an estimate in
{{COSTING_DIR}}. Setkind: assumption.
Quote the source line for each finding. Never invent a finding. Stop at 20 findings for each run.
RAID files
Write one file for each finding: {{DELIVERY_DIR}}/questions/Q-NNN.md.
---
id: Q-014
kind: question
status: open
raisedAt: <YYYY-MM-DD>
raisedBy: assistant
owner:
specRef: <spec path>#<heading>
taskRef:
ticket:
---
## Question
<one sentence>
## Answer
## Consequence
- Write all nine keys. Keep an empty key bare.
kindisquestion,risk,assumption,issueordependency.statusisopen,assigned,answeredorfolded.- Take the highest
Q-NNNof all file names and allidkeys. Add one. Pad to three digits. An empty register starts atQ-001. - A reworded question keeps its id.
- List the register first. Read the target path again just before each write. If it has content, take the next id.
- Never overwrite a file. Skip a clarification when a file holds it for the same
specRef. - Never delete a file. Set
status: foldedinstead. - Put an answer under
## Answer. Setstatus: answered. A clarification pair without an answer isopen. - Do not edit a spec. The user folds an answer into the spec as a separate change.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 85 lines · 46 tokens per session scan A a8bc27ecf49f
grill is a skill published in the GitHub repository me-cedric/agent-compass (3 stars, last pushed 4d ago), licensed MIT. It adds 46 tokens to every session and 764 once invoked, about $0.0002 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 2026-10-18.
Other skills, from other repositories
paperclip
Use for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.
paperclip-task-bridge
Create, comment on, update, and list Paperclip tasks from Hermes using scoped Paperclip API credentials.
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
process-mapper
Use when a BizOps lead, COO, or process-improvement owner needs to document an end-to-end business process (procurement, employee onboarding, incident handoff, customer-onboarding, claims adjudication) in BPMN-style notation, measure cycle times by stage, surface where work spends most of its time waiting vs. being…
strategic-alignment
Cascades strategy from boardroom to individual contributor. Detects and fixes misalignment between company goals and team execution. Covers strategy articulation, cascade mapping, orphan goal detection, silo identification, communication gap analysis, and realignment protocols. Use when teams are pulling in different…