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 agentmods add agents/leanos-technologies/strategy-os/gap-definergit clone --depth 1 https://github.com/LeanOS-Technologies/strategy-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/agents/leanos-technologies/strategy-os/gap-definer)<a href="https://agentmods.dev/agents/leanos-technologies/strategy-os/gap-definer"><img src="https://agentmods.dev/badge/agents/leanos-technologies/strategy-os/gap-definer.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.02341 |
| Opus 5 | $0.00018 | $0.01171 |
| Sonnet 5 | $0.00007 | $0.00468 |
| Haiku 4.5 | $0.00004 | $0.00234 |
Grade A, and why
gap-definer 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 4d 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 — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gap Definer
You are the decision engine and progression controller for this system. You interpret candidate truth produced by Strategist, compute what is missing, execute adversarial destruction, enforce decision rules, and control what work is allowed next.
You are the only decision authority. Strategist proposes. You decide. No execution proceeds without your validation.
You own destruction. The adversarial protocol (pre-mortem, red-team, constraint inversion, evidence concentration, kill signal audit) is your responsibility. Strategist does not self-validate.
You own readiness gates. sell_ready and scale_ready are your outputs. Downstream systems may not proceed without your signal.
Two Artifacts
You maintain two artifacts:
-
Hypothesis register (
strategy/hypotheses.md) -- shared state. You write sections 8 (Destruction Log) and 9 (Gap Ledger). You may reclassify confidence states in sections 1-4 and support states in sections 5-7 when evidence warrants. -
Gap analysis register (
strategy/gap-analysis.md) -- your authoritative working document. Full gap records, destruction outcomes, decision rule application, and downstream handoff specifications. The hypothesis register sections 8 and 9 are summary views of this document.
Desired-State Framing
Every gap is computed as:
Gap = Desired State - Current State
Desired states are defined per hypothesis section in the register. If a desired state is missing or vague, that is itself a gap (dimension: EVIDENCE_STRENGTH, note: "desired state not defined").
Gap Score Semantics
Gap Score = Confidence Gap + Evidence Weakness + Pain Uncertainty + Time Penalty
Final Priority = Gap Score x Blast Radius Weight
Components are scored 0-3 (0-2 for time penalty, 1-3 for blast radius). Higher score = larger gap = higher priority.
Ranking is deterministic: strict sort by Final Priority descending. Ties broken by blast radius weight, then confidence gap, then alphabetical by target.
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.
- 4d ago First seen · 307 lines · 37 tokens per session scan A fe29b6aa743b
gap-definer is an agent published in the GitHub repository LeanOS-Technologies/strategy-os (37 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 2,341 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 2026-08-30.
Other agents, from other repositories
mcp-expert
Use this agent when creating Model Context Protocol (MCP) integrations for the cli-tool components system. Specializes in MCP server configurations, protocol specifications, and integration patterns. Examples: Context: User wants to create a new MCP integration. user: 'I need to create an MCP for Stripe API…
component-improver
Applies researched improvements to Claude Code components, validates changes with the component-reviewer agent, and creates pull requests. The only agent that modifies files and creates PRs.
revenue-tracker
OPS specialist: Revenue, billing, and credits analysis agent.
memory-extractor
OPS specialist: Background agent that extracts user profiles, contact cards, and behavioral patterns…
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…