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 krokoko/cairn --skill design-strategygit clone --depth 1 https://github.com/krokoko/cairnWrote 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/krokoko/cairn/design-strategy)<a href="https://agentmods.dev/skills/krokoko/cairn/design-strategy"><img src="https://agentmods.dev/badge/skills/krokoko/cairn/design-strategy/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/krokoko/cairn/design-strategy"><img src="https://agentmods.dev/badge/skills/krokoko/cairn/design-strategy.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 | $0.00056 | $0.03506 |
| Opus 5 | $0.00028 | $0.01753 |
| Sonnet 5 | $0.00011 | $0.00701 |
| Haiku 4.5 | $0.00006 | $0.00351 |
Grade A, and why
design-strategy 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 8d 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 — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Verification Strategy
Design a tailored verification strategy for specific components or the full codebase. Produces a verification-strategy.md with per-component recommendations, oracle strategies, evidence pipeline design, and an implementation roadmap.
Workflow
Step 1: Load prior assessment
Search for verification-report.md in the codebase. If it exists, read the component breakdown, maturity tier, and identified gaps.
If no report exists, perform a lightweight discovery:
- Identify main components/modules from directory structure
- Check for existing tests, CI, type checking
- Classify each component by archetype and criticality
Step 2: Scope target components
- If the user specified a component path or name, focus on that component.
- Otherwise, prioritize components by: (1) high criticality with low verification, (2) autonomy candidates that need one more layer, (3) components with missing oracles.
Step 3: Apply decision framework
Load references/hybrid-strategies.md for archetype-to-stack mappings.
Load references/toolchain-catalog.md and references/toolchain-catalog-ecosystems.md for ecosystem-specific tool recommendations.
For each target component:
- Identify archetype: Deterministic lib, CRUD service, distributed/stateful, safety kernel, ML-backed, data pipeline, infrastructure/IaC, legacy monolith, agent-written
- Look up recommended stack: From the hybrid strategies reference
- Diff current vs recommended: What already exists? What is missing?
- Produce specific recommendations:
- Which tools/libraries to add
- Which files to create or modify
- Estimated effort (small/medium/large)
- Expected impact on verification maturity
Step 4: Design oracle strategy
Load references/oracle-patterns.md.
For each component, recommend the best oracle type:
| Component type | Recommended oracle approach |
|---|---|
| Pure functions | Exact expected output + property-based |
| User-facing behavior | Executable acceptance criteria (Gherkin/BDD) linked to requirements |
| API endpoints | Schema validation + contract tests |
| Data pipelines | Metamorphic relations + replay |
| ML models | Differential + statistical + human |
| State machines | Model checking + replay |
| UI components | Snapshot + visual regression + human |
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/eval-framework-operations.md 1.9 KB
- references/eval-framework.md 2.4 KB
- references/fitness-functions-implementation.md 4.0 KB
- references/fitness-functions.md 2.7 KB
- references/gate-design-patterns.md 6.5 KB
- references/generator-evaluator.md 4.1 KB
- references/harness-architecture.md 4.2 KB
- references/hybrid-strategies.md 5.5 KB
- references/oracle-patterns.md 5.5 KB
- references/safe-evolution.md 2.9 KB
- references/strategy-report-template.md 3.2 KB
- references/toolchain-catalog-ecosystems.md 3.2 KB
- references/toolchain-catalog.md 2.9 KB
- references/traceability-design.md 2.5 KB
- references/verification-cost-tiers.md 3.9 KB
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.
- 8d ago First seen · 299 lines · 56 tokens per session scan A 63242341652c
design-strategy is a skill published in the GitHub repository krokoko/cairn (14 stars, last pushed 4d ago), licensed Apache-2.0. It adds 56 tokens to every session and 3,506 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
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.
agent-loop
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor.
cross-task-learner
Enable agent loops to learn from similar past tasks and share patterns across loops.
infer-completion-criteria
Infer measurable completion criteria for an agent-loop task from project docs, code, and AIWG standards when the user has not supplied --completion explicitly.
aiwg-language-map
AIWG addons + extensions language map — categories, curated discover phrases, and per-bundle pointers covering everything beyond the framework quickrefs.
aiwg-regenerate-claude
Regenerate CLAUDE.md for Claude Code with hook file architecture.