Use this workflow when a result is a count, ratio, percentage, coverage number, or pass/fail total.
Scanned 9/2/2026
Install to Claude Code
npx -y skills add sleep2agi/agent-network --skill 1.0.0 --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of 1.0.0?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/sleep2agi-1-0-0-agent-network)More formats (shields.io, HTML) on the badges page.
# Invariant denominator check
Use this workflow when a result is a count, ratio, percentage, coverage number,
or pass/fail total.
## Name the measured object
Before trusting the number, write the object being counted:
```text
numerator: <what increments the count>
denominator: <the complete set it is divided by or compared against>
scope: <repo, network, account, runtime, date range, or file set>
```
A number can be arithmetically correct and still answer the wrong question.
## Check same-value traps
Look for cases where two different states produce the same output:
1. not checked vs checked and zero;
2. no data vs data unavailable;
3. no matching item vs matching item hidden by permissions;
4. all targets passed vs only a subset ran;
5. same author account vs same human or agent.
If two states share one value, add a separate field, log line, or exit code to
make them distinguishable.
## Verify the denominator
Use an independent listing command for the denominator before interpreting the
result. Examples include a file list, account list, test inventory, task list,
or PR search result. Record the command when the denominator is part of the
claim.
## Report with scope
Phrase the result with its denominator:
```text
41/41 checks passed for <exact suite>
```
Do not shorten it to "all checks passed" unless the exact universe of checks is
obvious from the same sentence.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.