Borrowing it
Nothing to install: this file belongs to caipe-io/ai-platform-engineering. 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/caipe-io/ai-platform-engineering/main/.claude/skills/run-caipe-integration-tests/SKILL.mdgit clone --depth 1 https://github.com/caipe-io/ai-platform-engineeringWrote 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/caipe-io/ai-platform-engineering/run-caipe-integration-tests)<a href="https://agentmods.dev/skills/caipe-io/ai-platform-engineering/run-caipe-integration-tests"><img src="https://agentmods.dev/badge/skills/caipe-io/ai-platform-engineering/run-caipe-integration-tests/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/caipe-io/ai-platform-engineering/run-caipe-integration-tests"><img src="https://agentmods.dev/badge/skills/caipe-io/ai-platform-engineering/run-caipe-integration-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 90 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 90 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00657 |
| Opus 5 | $0.00010 | $0.00329 |
| Sonnet 5 | $0.00004 | $0.00131 |
| Haiku 4.5 | $0.00002 | $0.00066 |
Grade A, and why
run-caipe-integration-tests scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf http://localhost:8000/.well-known/agent.json > /dev/null 2>&1 && echo "0.3.0 OK" || echo "0.3.0 NOT RUNNING" How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
Goal
Run integration tests against the local Docker Compose dev environment. This command orchestrates the streaming testing skill and optionally the full agent integration tests.
Execution Steps
1. Parse arguments
Interpret the user's input to determine which test suites to run:
- No arguments or
"all": Run streaming comparison + agent validation "streaming"or"stream": Run only the streaming comparison"agents"or"agent": Run only agent checkpoint validation"metadata"or"analyze": Run metadata analysis on an existing capture- A quoted query string (e.g.
"what is caipe?"): Run streaming comparison with that query
2. Pre-flight checks
Verify the environment is ready:
# Check Docker is running
docker info > /dev/null 2>&1
# Check supervisors
curl -sf http://localhost:8000/.well-known/agent.json > /dev/null 2>&1 && echo "0.3.0 OK" || echo "0.3.0 NOT RUNNING"
curl -sf http://localhost:8041/.well-known/agent.json > /dev/null 2>&1 && echo "0.2.41 OK" || echo "0.2.41 NOT RUNNING"
If a supervisor is not running, tell the user and suggest:
docker restart caipe-supervisor caipe-supervisor-041
3. Run streaming comparison (if applicable)
Use the streaming testing skill:
./skills/streaming-testing/run_comparison.sh "${QUERY:-what can you do?}"
This runs: health check -> capture from both supervisors -> metadata analysis -> side-by-side comparison.
Report the key findings:
- Time to first content (both versions)
- Any safety check failures (marker leaks, metadata leaks)
- Artifact breakdown differences
4. Run agent validation (if applicable)
./skills/persistence/validate_agent_checkpoints.sh
Report pass/fail summary.
5. Run Python unit tests (always)
PYTHONPATH=. uv run pytest tests/test_slack_narration_typing_status.py tests/test_streaming_e2e.py -v -m "not integration" --tb=short
Report pass/fail count.
6. Summary
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.
- 11d ago First seen · 91 lines · 19 tokens per session scan A eccce1c5992f
run-caipe-integration-tests is a skill published in the GitHub repository caipe-io/ai-platform-engineering (408 stars, last pushed today), licensed Apache-2.0. It adds 19 tokens to every session and 657 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
mcp-app-verification
Comprehensive verification checklists for MCP Apps. Tests with basic-host reference, validates handler-before-connect, text fallback, resource URI linking, single-file bundling, host styling, CSP, and legacy pattern detection.
behavior-contract
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
quality-hooks
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.
hook-management
Session-scoped hook lifecycle management with enable/disable/status controls, execution profiling, and color-coded performance alerts.
spec-execution
6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress tracking with quality-gated convergence.
eval-harness
Evaluation harness for testing agent and skill quality through structured benchmarks, regression tests, and quality scoring.