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/t-rav/hydraflow/hf.validate-tests-before-commitnpx skills add T-rav/hydraflow --skill hf.validate-tests-before-commitgit clone --depth 1 https://github.com/T-rav/hydraflowWhat 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 | $0.00013 | $0.01364 |
| Opus 5 | $0.00006 | $0.00682 |
| Sonnet 5 | $0.00003 | $0.00273 |
| Haiku 4.5 | $0.00001 | $0.00136 |
Grade C, and why
hf.validate-tests-before-commit scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
echo "BLOCKED: uv is not installed. Install it: curl -LsSf https://astral.sh/uv/install.sh | sh" >&2 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
echo "BLOCKED: uv is not installed. Install it: curl -LsSf https://astral.sh/uv/install.sh | sh" >&2 How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hf.validate-tests-before-commit
#!/bin/bash
# Hook: Validate tests exist for staged changes and pass before allowing commit.
# Fires on PreToolUse for Bash commands matching git commit.
# Blocks commit if:
# 1. --no-verify or --no-hooks flags are used
# 2. Python source files are staged without corresponding test files
# 3. Tests for affected services fail
set -euo pipefail
INPUT=$(cat)
COMMAND=$(echo "$INPUT" | jq -r '.tool_input.command // empty')
CWD=$(echo "$INPUT" | jq -r '.cwd // empty')
# Only intercept git commit commands
if ! echo "$COMMAND" | grep -qE '(^|\s|&&\s*|;\s*)git commit'; then
exit 0
fi
# Block --no-verify / --no-hooks (forbidden per CLAUDE.md)
if echo "$COMMAND" | grep -qE '\-\-no-verify|\-\-no-hooks'; then
echo "BLOCKED: --no-verify and --no-hooks are forbidden per CLAUDE.md." >&2
echo "Fix code issues first, then commit cleanly." >&2
exit 2
fi
# Resolve project root from git toplevel (CWD may be a subdirectory)
PROJECT_ROOT=$(git -C "$CWD" rev-parse --show-toplevel 2>/dev/null || echo "$CWD")
cd "$PROJECT_ROOT"
# Get staged files early — skip expensive checks for non-source commits
STAGED_FILES=$(git diff --cached --name-only 2>/dev/null || true)
if [ -z "$STAGED_FILES" ]; then
exit 0 # Nothing staged, let git handle it
fi
# Fast exit: if no source code is staged, skip lint and tests entirely
HAS_SOURCE=$(echo "$STAGED_FILES" | grep -E '\.(py|ts|tsx|js|jsx)$' || true)
if [ -z "$HAS_SOURCE" ]; then
exit 0 # Config/docs/YAML/Dockerfile-only commit, no lint or test needed
fi
# Require uv for running Python
if ! command -v uv &>/dev/null; then
echo "BLOCKED: uv is not installed. Install it: curl -LsSf https://astral.sh/uv/install.sh | sh" >&2
exit 2
fi
# Run lint checks (only reached for commits with source code)
echo "Running lint checks..." >&2
if ! make -C "$PROJECT_ROOT" lint-check > /dev/null 2>&1; then
echo "BLOCKED: Lint check failed." >&2
echo "Run 'make lint' to auto-fix formatting and import issues, then re-stage." >&2
exit 2
fi
echo "Lint checks passed." >&2
# Get staged Python source files (excluding tests, configs, migrations, __init__)
SOURCE_FILES=$(echo "$STAGED_FILES" | grep '\.py$' \
| grep -vE '(test_|_test\.py|conftest\.py|/tests/|__init__\.py|migrations?/|setup\.py|manage\.py)' \
|| true)
# Get staged test files
TEST_FILES=$(echo "$STAGED_FILES" | grep -E '(test_[^/]*\.py$|_test\.py$)' || true)
# If there are source changes but no test files staged, block the commit
if [ -n "$SOURCE_FILES" ] && [ -z "$TEST_FILES" ]; then
echo "BLOCKED: Python source files staged without corresponding test files." >&2
echo "" >&2
echo "Source files staged:" >&2
echo "$SOURCE_FILES" | sed 's/^/ - /' >&2
echo "" >&2
echo "Per CLAUDE.md: Every new function/class/feature MUST include tests." >&2
echo "Write tests for your changes and stage them before committing." >&2
exit 2
fi
# Determine which services are affected and run their tests
SERVICES_TO_TEST=""
# Auto-discover affected top-level directories from staged files
TOP_DIRS=$(echo "$STAGED_FILES" | sed -n 's|^\([^/]*\)/.*|\1|p' | sort -u)
for dir in $TOP_DIRS; do
# Skip non-testable directories
case "$dir" in
.github|.claude|.hydraflow|docs|ui|venv|node_modules) continue ;;
esac
if [ -d "$PROJECT_ROOT/$dir/tests" ]; then
SERVICES_TO_TEST="$SERVICES_TO_TEST $dir"
fi
done
# Also check root-level test directory
if echo "$STAGED_FILES" | grep -q "^tests/"; then
SERVICES_TO_TEST="$SERVICES_TO_TEST root"
fi
if [ -z "$SERVICES_TO_TEST" ]; then
exit 0 # No testable service changes (docs, configs, etc.)
fi
# Run tests for each affected service
FAILED_SERVICES=""
for service in $SERVICES_TO_TEST; do
if [ "$service" = "root" ]; then
TEST_DIR="$PROJECT_ROOT"
TEST_PATH="tests/"
else
TEST_DIR="$PROJECT_ROOT/$service"
TEST_PATH="tests/"
fi
if [ -d "$TEST_DIR/$TEST_PATH" ]; then
echo "Running tests for $service..." >&2
if ! (cd "$TEST_DIR" && PYTHONPATH=. VIRTUAL_ENV="$PROJECT_ROOT/venv" uv run --active pytest -m "not integration and not system_flow and not smoke" -q "$TEST_PATH" 2>&1); then
FAILED_SERVICES="$FAILED_SERVICES $service"
fi
fi
done
if [ -n "$FAILED_SERVICES" ]; then
echo "" >&2
echo "BLOCKED: Tests failed for:$FAILED_SERVICES" >&2
echo "Fix failing tests before committing." >&2
exit 2
fi
echo "All tests passed for affected services." >&2
exit 0
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 · 141 lines · 13 tokens per session scan C a906ab14c80d
hf.validate-tests-before-commit is a skill published in the GitHub repository T-rav/hydraflow (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 13 tokens to every session and 1,364 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
develop
Run /develop to build a feature, UI or backend, from an approved design, a page, component, API, service, or data slice. If something load bearing is undecided and no spec records it, it stops and routes you to /architect; otherwise it reads the spec plus AGENTS.md, builds, and advances the scope.
sync
Run /sync as the last step after a change is complete, around merge, to keep durable knowledge current. Updates root and nested AGENTS.md, reconciles the scope from repo evidence, and flags specs the change made stale. Surgical edits only: it adds lines, and rewrites single lines it owns. Never a whole section, never…
test
Run /test to write a test suite for code you just built or changed, after implementing a feature, route, or fix. Targets uncommitted changes automatically, reads test preferences.json for your framework (asks and saves it if absent), and picks the right strategy per file: happy path, edge cases, error states…
document
Run /document pr | changelog | release-note | postmortem (or let it ask) to write the human facing prose about a change. Drafts from the real commits and diff, writing to the right place. Does not write code, tests, or specs.
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…