Borrowing it
Nothing to install: this file belongs to LeanOS-Technologies/strategy-os. 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/LeanOS-Technologies/strategy-os/main/.claude/skills/gap-computing-ledger/SKILL.mdgit 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/skills/leanos-technologies/strategy-os/gap-computing-ledger)<a href="https://agentmods.dev/skills/leanos-technologies/strategy-os/gap-computing-ledger"><img src="https://agentmods.dev/badge/skills/leanos-technologies/strategy-os/gap-computing-ledger/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/leanos-technologies/strategy-os/gap-computing-ledger"><img src="https://agentmods.dev/badge/skills/leanos-technologies/strategy-os/gap-computing-ledger.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 | $0.01721 |
| Opus 5.5 | $0.00018 | $0.00688 |
| Sonnet 5.5 | $0.00009 | $0.00344 |
| Haiku 4.5 | $0.00005 | $0.00172 |
Grade A, and why
gap-computing-ledger 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 1mo 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gap Ledger Computation
Compute the distance between desired state and current state for each hypothesis and proposal in the register. Produce scored, ranked gap records that drive prioritization.
Process
Step 1: Extract Desired and Current States [S]
For each hypothesis section (Problem, Segment, Unit Economics, Value Proposition) and each proposal section (Growth Architecture, Solution Design, GTM Plan):
- Read the Desired State block. List every condition under "SUPPORTED means."
- Read the Current State block. For each condition, record its fulfillment status: MET, PARTIAL, MISSING, or CONTRADICTED.
- If a section has no Desired State block, mark the entire section as having a gap of type EVIDENCE_STRENGTH with note "no desired state defined."
Gate: states_extracted: bool -- every register section has a desired/current pair or is flagged as missing.
- Pass: Step 2.
- Fail: flag missing sections and proceed with available data.
Step 2: Score Each Gap [R]
For each condition that is not MET, compute a gap record using these scales:
Confidence Gap (0-3):
| Current Confidence | Desired Confidence | Score |
|---|---|---|
| unvalidated | supported | 3 |
| researched | supported | 2 |
| supported but thin | supported (robust) | 1 |
| supported | supported | 0 |
Evidence Weakness (0-3):
| Evidence Profile | Score |
|---|---|
| Only T3 / assertion-heavy | 3 |
| Mostly T2 | 2 |
| Mixed T1/T2 but thin | 1 |
| Enough T1 for decision | 0 |
Pain Uncertainty (0-3):
| Pain Clarity | Score |
|---|---|
| Unclear whether pain is real or acute | 3 |
| Partially clear | 2 |
| Mostly clear | 1 |
| Clear | 0 |
Time Penalty (0-2):
| Deadline Status | Score |
|---|---|
| Exceeded | 2 |
| Due or near due | 1 |
| Within deadline | 0 |
Blast Radius Weight (1-3):
| Impact If Wrong | Weight |
|---|---|
| Strategy collapses | 3 |
| One major hypothesis must change | 2 |
| Local revision only | 1 |
Final Priority Score:
Final Priority = (Confidence Gap + Evidence Weakness + Pain Uncertainty + Time Penalty) x Blast Radius Weight
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.
- 1mo ago First seen · 185 lines · 46 tokens per session scan A a6ac33c953b0
gap-computing-ledger is a skill published in the GitHub repository LeanOS-Technologies/strategy-os (39 stars, last pushed 6mo ago), licensed MIT. It adds 46 tokens to every session and 1,721 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 2026-08-30.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
qa-test-planner
Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.
email-sequence
When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions "email sequence," "drip campaign," "nurture sequence," "onboarding emails," "welcome sequence," "re-engagement emails," "email automation," or "lifecycle…
emerging-techniques-long-context
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases…
prompt-engineering-guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.
content-research-writer
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.