Borrowing it
Nothing to install: this file belongs to andrew-yangy/gru-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/andrew-yangy/gru-ai/main/.claude/skills/report/SKILL.mdgit clone --depth 1 https://github.com/andrew-yangy/gru-aiWrote 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/andrew-yangy/gru-ai/report)<a href="https://agentmods.dev/skills/andrew-yangy/gru-ai/report"><img src="https://agentmods.dev/badge/skills/andrew-yangy/gru-ai/report/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/andrew-yangy/gru-ai/report"><img src="https://agentmods.dev/badge/skills/andrew-yangy/gru-ai/report.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 | $0.00052 | $0.03890 |
| Opus 5 | $0.00026 | $0.01945 |
| Sonnet 5 | $0.00010 | $0.00778 |
| Haiku 4.5 | $0.00005 | $0.00389 |
Grade A, and why
report 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 — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CEO Report
Role Resolution
Read .claude/agent-registry.json to map roles to agent names. Domain labels in this report use role titles (CTO, CPO, CMO, COO) -- resolve to actual agent names from the registry when generating output.
Generate a CEO report. Tier: $ARGUMENTS (default: headline)
Step 1: Determine Tier
Parse $ARGUMENTS:
- If empty or "headline" or "h" → headline tier
- If "summary" or "s" or "daily" or "d" → summary tier
- If "deep" or "weekly" or "w" → deep tier
Step 2: Gather Data
What to read depends on the tier. Higher tiers include everything from lower tiers.
Headline Tier Data (minimal — fast)
.context/directives/*/directive.json— count active goals.context/directives/*/projects/*/project.json— count active/completed/blocked projects, identify recently completed.context/backlog.json— count P0 items needing CEO.context/directives/*.json— count pending directives (filter by status: pending).context/reports/— scan 3 most recent for unaddressed high-risk follow-ups.context/healthchecks/latest/*.json— quick health status (pass/fail)- Run
npm run type-check— build status (pass/fail only, don't show errors here)
Summary Tier Data (adds detail on top of headline)
All headline data, PLUS:
.context/vision.md— for context on what matters.context/preferences.md— CEO standing orders.context/intel/latest/*.json— latest scout outputs per agent~/.conductor/scheduler.jsonand~/.conductor/scheduler.log— autopilot status- Recent directive reports — corrections caught data
- Run git commands for recent changes:
# Recent commits on main (last 24h)
git log --oneline --since="24 hours ago" main
# Active worktrees
git worktree list
# Recently modified context files
find .context/ -name "*.md" -mtime -1 -type f | head -20
- Active projects with no recent progress
- Failed/blocked initiatives from recent directives
- OKR progress from
.context/directives/*/directive.json
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 · 381 lines · 52 tokens per session scan A 28ea952870ca
report is a skill published in the GitHub repository andrew-yangy/gru-ai (153 stars, last pushed 6mo ago), licensed MIT. It adds 52 tokens to every session and 3,890 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
building
Implementation skill for writing production code with TDD. Covers the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns. Loaded by component-builder and bug-investigator.
diff-driven-docs
Use when a BUILD phase completes, a commit is staged, or a PR is about to be created, and the diff has not yet been reflected in documentation. Also use when the user says "update docs", "sync docs", "document this", or asks whether documentation is up to date.
exploration
Two-mode exploration skill: (1) design dialogue — turn rough ideas into validated designs through collaborative interview before planning; (2) spike — throwaway code answering ONE design question, deleted or absorbed, never shipped. Router invokes mode via dispatch context.
memory-and-handoff
Two-mode skill: (1) session memory — load/persist durable workflow state under .cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable, secrets-redacted export for a coworker, different tool, or fresh non-cc10x session.
plan-review-gate
Use after saving a non-trivial plan or decision RFC when a fail-closed feasibility, completeness, and alignment review must block execution.
architecture
Greenfield architecture design: map functionality flows, draw components, design APIs, classify dependencies, plan observability. For multi-component, API, schema, auth, or integration-heavy work. For retrofitting existing code, use codebase-hygiene instead.