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 skills/zircote/subcog/test-runnernpx skills add zircote/subcog --skill test-runnergit clone --depth 1 https://github.com/zircote/subcogWhat 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 | $0.00000 | $0.01826 |
| Opus 5 | $0.00000 | $0.00913 |
| Sonnet 5 | $0.00000 | $0.00365 |
| Haiku 4.5 | $0.00000 | $0.00183 |
Grade A, and why
test-runner 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 2d 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subcog Test Runner Skill
Orchestrate automated functional tests for Subcog MCP tools. Validates all documented functionality against expected behavior.
Trigger Phrases
- "run subcog tests", "test subcog", "/run-tests"
- "validate subcog functionality", "functional tests"
- "run automated tests", "execute test suite"
Quick Reference
| Mode | What It Does | Trigger |
|---|---|---|
| Full | Run all tests | /run-tests |
| Category | Run specific category | /run-tests --category crud |
| Tag | Run tests with tag | /run-tests --tag critical |
| Dry-run | Show tests without running | /run-tests --dry-run |
Execution Strategy
Key Behaviors:
- Tests execute ONE AT A TIME for clear validation
- Each test waits for user confirmation ("next") before proceeding
- Failed tests are logged but don't block subsequent tests
- Variables saved from tests are substituted in dependent tests
Workflow
Phase 1: Initialization
-
Verify Environment
Call subcog_status to verify MCP server is running -
Load Test Suite
- Read
tests/functional/tests.yaml - Parse test definitions
- Build dependency graph
- Filter by category/tag if specified
- Read
-
Initialize State Write to
.claude/test-state.json:{ "mode": "running", "total_tests": 50, "current_index": 0, "current_test": null, "results": [], "saved_vars": {}, "started_at": "2024-01-20T12:00:00Z" } -
Show Test Plan
# Subcog Functional Test Suite Total tests: 50 Categories: initialization (4), crud (10), search (6), ... Type 'next' to begin, 'skip' to skip a test, 'abort' to stop.
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.
- 2d ago First seen · 290 lines · 0 tokens per session scan A 287ac7dad7b5
test-runner is a skill published in the GitHub repository zircote/subcog (28 stars, last pushed 29d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,826 tokens. 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
codebase-exploration
Explore and understand codebases using SocratiCode semantic search, dependency graphs, and context artifacts. Use when exploring code, understanding architecture, finding functions/types, analysing dependencies, searching database schemas or API specs, or when socraticode/codebasesearch tools are available. Activates…
codebase-management
Set up, index, and manage SocratiCode codebase indexing. Use when the user wants to index a project, check infrastructure health, start/stop file watching, configure context artifacts, troubleshoot indexing issues, manage the code graph, or any SocratiCode administrative task. Activates when the user mentions…
cocosearch-review-pr
Use when reviewing a GitHub PR or GitLab MR by URL. Fetches diff and metadata via API, then uses CocoSearch for blast radius analysis, dependency impact, pattern consistency, and test coverage assessment. Read-only by default; optionally pushes findings back as inline PR/MR comments after your confirmation.
cocosearch-add-language
Use when adding support for a new programming language or config format to CocoSearch. Guides through all paths (handler, symbol extraction, context expansion) with registration checklists. For grammar handlers, use cocosearch-add-grammar.
cocosearch-add-extractor
Use when adding a dependency extractor for a language or grammar. Guides through pre-checks, extractor implementation, optional module resolver, tests, and registration. Enables deps tree, deps impact, and dependency-enriched search for the target language.
cocosearch-add-grammar
Use when adding a grammar handler for domain-specific file formats that share a base language extension (e.g., GitHub Actions within YAML). Guides through YamlGrammarBase inheritance, content validation, separator spec, metadata extraction, tests, and registration.