Borrowing it
Nothing to install: this file belongs to T-rav/hydraflow. 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/T-rav/hydraflow/staging/.codex/skills/hf.audit-integration-tests/SKILL.mdgit clone --depth 1 https://github.com/T-rav/hydraflowWrote 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/t-rav/hydraflow/hf.audit-integration-tests)<a href="https://agentmods.dev/skills/t-rav/hydraflow/hf.audit-integration-tests"><img src="https://agentmods.dev/badge/skills/t-rav/hydraflow/hf.audit-integration-tests.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 | $0.00009 | $0.02182 |
| Opus 5 | $0.00005 | $0.01091 |
| Sonnet 5 | $0.00002 | $0.00436 |
| Haiku 4.5 | $0.00001 | $0.00218 |
Grade A, and why
hf.audit-integration-tests scanned grade A with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **HTTP clients**: httpx, requests, aiohttp, urllib calls to external services Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Subprocess calls**: asyncio.create_subprocess_exec, subprocess.run, os.system How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Integration Test Audit
Run a comprehensive integration test audit across the entire repo. Dynamically discovers external dependencies in source code, inventories existing integration tests, identifies coverage gaps, flags ugly/outdated tests, and creates GitHub issues for findings.
Instructions
-
Resolve configuration before doing anything else:
- Run
echo "$HYDRAFLOW_GITHUB_REPO"— if set, use it as the target repo (e.g.,owner/repo). If empty, rungit remote get-url originand extract theowner/reposlug (striphttps://github.com/prefix and.gitsuffix). - Run
echo "$HYDRAFLOW_GITHUB_ASSIGNEE"— if set, use it as the issue assignee. If empty, extract the owner from the repo slug (the part before/). - Use
hydraflow-planas the label for created issues. - Store resolved values as
$REPO,$ASSIGNEE,$LABEL.
- Run
-
Discover project structure:
- Use Glob to find all
*.pysource files, excluding.venv/,venv/,__pycache__/,node_modules/,dist/,build/. - Separate into SOURCE files and TEST files (any file under a
tests/ortest/directory, or matchingtest_*.py). - Identify external dependencies by scanning source files for: subprocess calls, HTTP clients, database connections, message queues, file I/O, external CLI tools, API clients.
- Use Glob to find all
-
Launch agents in parallel using
Taskwithrun_in_background: trueandsubagent_type: "general-purpose":- Agent 1: External dependency mapping & gap analysis — Maps all external dependencies in source code, cross-references with existing integration tests.
- Agent 2: Test quality & anti-pattern detection — Reviews existing tests for ugly patterns, false integration tests, and outdated code.
- Agent 3: Cross-module integration gaps — Identifies integration points between modules and missing end-to-end test coverage.
-
Wait for all agents to complete.
-
After all finish, run
gh issue list --repo $REPO --label $LABEL --state open --search "integration test" --limit 200to show the user a final summary of all issues created.
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 · 188 lines · 9 tokens per session scan A 4ed0c1e5c699
hf.audit-integration-tests is a skill published in the GitHub repository T-rav/hydraflow (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 9 tokens to every session and 2,182 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
debug
Run /debug to find and fix a bug's root cause: a test failing for an unclear reason, /check verify finding a failure, or behavior being wrong. Runs a reproduce, localize, hypothesize, test, fix, verify loop, makes the minimal fix, and hands a regression test to /test. No features, no extra refactors.
check
Confirm a change before merge. /check verify drives the real app to prove behavior against the spec (every acceptance criterion met, every surface built). /check review runs a senior code review on a fresh model, one that did not write the code. Verify after /develop, review before a PR. Writes to docs/reviews/, never…
criterion-verification-map
Transform acceptance criteria into plan-time runnable verification commands (behavioral, API, UI, error, config, data, contract types) with expected evidence shapes, then execute at verify time and assemble evidence bundles with honest completeness subsections (untested paths, known limitations, adversarial cases…
goal-evaluator
Evaluate a FlowGoal against its evidence ledger and update lifecycle status to one of {pass, incomplete, fail, needshumanreview, blocked} by running deterministic verification commands first, then (when stopHookEnforcement=evaluator-loop or explicit /flow:goal evaluate invocation) dispatching the goal-evaluator-judge…
holdout-validation
Cross-reference agent self-review claims against actual file state using hidden holdout scenarios, producing mapped P1/P2/P3 findings that reference visible acceptance criteria only. Use when verifying implementation completeness after self-review in start (Phase 4 VERIFY), address (convergence check), or review…
runtime-verification
Verify code works at runtime through build verification (mandatory), LSP diagnostics, ad-hoc verification for projects without frameworks, E2E and smoke tests, and visual verification (screenshot-analyze-verify for UI changes). Skip whitelist strictly enforced (markdown-only, config-only, dependency-bump-only with…