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 adolfousier/opencrabs --skill cost-estimategit clone --depth 1 https://github.com/adolfousier/opencrabsWrote 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/adolfousier/opencrabs/cost-estimate)<a href="https://agentmods.dev/skills/adolfousier/opencrabs/cost-estimate"><img src="https://agentmods.dev/badge/skills/adolfousier/opencrabs/cost-estimate.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 5.1 | $0.00019 | $0.01425 |
| Opus 5 | $0.00010 | $0.00713 |
| Sonnet 5 | $0.00004 | $0.00285 |
| Haiku 4.5 | $0.00002 | $0.00143 |
Grade A, and why
cost-estimate 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 7d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scan this entire codebase and produce a professional cost estimate and valuation report. Analyze:
-
Codebase inventory: Count files, lines of code by language, modules, API integrations, external services, database schemas, UI components, and any complex subsystems.
-
Complexity assessment: Identify the hardest parts — real-time features, protocol implementations, security layers, multi-platform support, API integrations (especially government/enterprise APIs that require domain expertise), custom parsers, streaming, WebSocket/SSE, OAuth flows, etc.
-
Human team estimate: Calculate what a real development team would need to build this from scratch. Use current US market rates (2025-2026):
- Senior full-stack developer: $125-175/hr
- Backend specialist: $150-200/hr
- DevOps/infra: $140-180/hr
- UI/UX: $100-150/hr
- Project management overhead: 15-20%
- QA/testing: 15-20% of dev time
- Estimate across 4 team sizes: Solo dev, Lean Startup (2-3), Growth Co (4-6), Enterprise (8+)
-
AI comparison: Estimate AI-assisted hours actually spent (based on git history, commit frequency, time span from first to latest commit). Calculate speed multiplier and value per hour.
-
Integration complexity: For each external integration (APIs, channels, protocols, third-party services), assess:
- API stability and breaking change risk (how often does the upstream API change?)
- Authentication complexity (OAuth, tokens, QR pairing, binary handshakes)
- Rate limiting and quota constraints
- Failure modes and required retry/fallback logic
- Vendor lock-in risk and migration difficulty
- Rate each integration: Low / Medium / High / Critical maintenance burden
-
Test coverage and CI: Analyze what exists and what a production build would need:
- Current test coverage (count ALL test types:
#[test],#[tokio::test],#[rstest], proptest — not just#[test]) - Missing coverage gaps (what subsystems have zero tests?)
- Estimated hours to reach production-grade coverage (70-80%)
- CI pipeline requirements (build matrix, linting, security scanning, release automation)
- Cost of CI infrastructure (GitHub Actions minutes, build times for Rust)
- Current test coverage (count ALL test types:
-
Ongoing maintenance and operational cost: The hidden costs after "it works":
- Monthly maintenance hours by category (dependency updates, security patches, API breaking changes, bug fixes)
- On-call burden estimate — how many integration points can break independently? What's the expected incident frequency?
- Dependency risk — count direct deps, assess which are unmaintained/fragile/pre-1.0
- Upgrade burden — major version bumps expected in next 12 months
- Annual maintenance cost (hours x rate) for a solo maintainer vs. a team
- Technical debt estimate — what shortcuts exist that will cost more later?
-
Fair market valuation: Before estimating valuation, ASK THE USER for context that affects the valuation model. Prompt them with:
"To produce an accurate valuation, I need some context:
- Business model — Is this OSS, SaaS, enterprise-licensed, consulting, or something else?
- Revenue — Any current MRR/ARR? If pre-revenue, is monetization planned?
- Traction — GitHub stars, clones, downloads, active users, community size?
- Team — Solo maintainer or team? Full-time or side project?
- Funding — Bootstrapped, funded, or seeking investment?
- Intent — Are you valuing for acquisition, fundraising, insurance, or just curiosity?"
Wait for the user's answers, then use the appropriate valuation methods:
Always include:
- Cost-to-reproduce — what would it cost to rebuild from scratch today? Use the Grand Total figures.
- Replacement cost — what would a company pay to buy equivalent functionality off the shelf? If no equivalent exists, note that — it increases strategic value.
- Strategic/acqui-hire value — what would an acquirer pay for the technology + expertise? Consider: unique integrations, competitive moat, time-to-market advantage, and talent cost savings.
- Risk-adjusted valuation — discount for: bus factor, technical debt, test coverage gaps, dependency risks, market competition.
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.
- 7d ago First seen · 87 lines · 19 tokens per session scan A 7b93fe926460
cost-estimate is a skill published in the GitHub repository adolfousier/opencrabs (927 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 1,425 once invoked, about $0.0001 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
agent-agent
Agent skill for agent - invoke with $agent-agent.
agent-crdt-synchronizer
Agent skill for crdt-synchronizer - invoke with $agent-crdt-synchronizer.
agent-performance-benchmarker
Agent skill for performance-benchmarker - invoke with $agent-performance-benchmarker.
agent-quorum-manager
Agent skill for quorum-manager - invoke with $agent-quorum-manager.
agent-topology-optimizer
Agent skill for topology-optimizer - invoke with $agent-topology-optimizer.
agent-benchmark-suite
Agent skill for benchmark-suite - invoke with $agent-benchmark-suite.