hydraflow: Skill for Claude Code

.codex/skills/hf.enforce-plan-and-explore/SKILL.md

hf.enforce-plan-and-explore is a skill for Claude Code, Codex from T-rav/hydraflow. It costs 15 tokens per session (710 once invoked), scanned A, original, Apache-2.0.

A warning hook for Python projects that reminds developers to explore the code and make a plan before editing source files. It checks whether recent reading or searching has happened and warns once during a session.

In plain words
What is it for?
Use it when you want a lightweight reminder to inspect relevant files and plan Python source changes before editing.
Why use it?
It helps prevent changes made without understanding the surrounding code or deciding on an approach first.

Skill for Claude CodeCodex

Written for Claude Code and Codex: ${CLAUDE_PROJECT_DIR variable, but also installed under .codex/.

This is T-rav/hydraflow's own configuration. It tells Claude Code and Codex how to work on hydraflow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything hydraflow configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/T-rav/hydraflow/staging/.codex/skills/hf.enforce-plan-and-explore/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/T-rav/hydraflow

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for hf.enforce-plan-and-explore

README.md
[![agentmods](https://agentmods.dev/badge/skills/t-rav/hydraflow/hf.enforce-plan-and-explore/github.svg)](https://agentmods.dev/skills/t-rav/hydraflow/hf.enforce-plan-and-explore)
Your own site
<a href="https://agentmods.dev/skills/t-rav/hydraflow/hf.enforce-plan-and-explore"><img src="https://agentmods.dev/badge/skills/t-rav/hydraflow/hf.enforce-plan-and-explore/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.

agentmods 80×15 button for hf.enforce-plan-and-explore

Your own site · 80×15
<a href="https://agentmods.dev/skills/t-rav/hydraflow/hf.enforce-plan-and-explore"><img src="https://agentmods.dev/badge/skills/t-rav/hydraflow/hf.enforce-plan-and-explore.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 710 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00015 $0.00710
Opus 5 $0.00008 $0.00355
Sonnet 5 $0.00003 $0.00142
Haiku 4.5 $0.00002 $0.00071

Measured 8d ago against content hash 0fb13579a24f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

hf.enforce-plan-and-explore 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.

.codex/skills/hf.enforce-plan-and-explore/SKILL.md · 69 lines

What it actually says

hf.enforce-plan-and-explore

#!/bin/bash
# Hook: Warn if editing source code without prior exploration or planning.
# Fires on PreToolUse for Edit tool.
# Warns ONCE per session (4-hour window), does not block.
# Only checks Python source files (skips tests, configs, __init__).

set -euo pipefail

INPUT=$(cat)
FILE_PATH=$(echo "$INPUT" | jq -r '.tool_input.file_path // empty')

# Only check Python source files
if ! echo "$FILE_PATH" | grep -qE '\.py$'; then
  exit 0
fi

# Skip test files, configs, __init__, migrations, scripts
if echo "$FILE_PATH" | grep -qE '(test_|_test\.py|conftest\.py|/tests/|__init__\.py|migrations?/|setup\.py|/scripts/)'; then
  exit 0
fi

PROJECT_DIR="${CLAUDE_PROJECT_DIR:-$(pwd)}"
MARKER_DIR="/tmp/claude-code-markers/$(echo -n "$PROJECT_DIR" | md5)"
mkdir -p "$MARKER_DIR"

# Check if already warned this session (within last 4 hours)
WARNED_MARKER="$MARKER_DIR/warned"
if [ -f "$WARNED_MARKER" ] && [ -n "$(find "$WARNED_MARKER" -mmin -240 2>/dev/null)" ]; then
  exit 0
fi

WARNINGS=""

# Check for exploration (Read/Grep marker within last 4 hours)
EXPLORE_MARKER="$MARKER_DIR/explored"
if [ ! -f "$EXPLORE_MARKER" ] || [ -z "$(find "$EXPLORE_MARKER" -mmin -240 2>/dev/null)" ]; then
  WARNINGS="${WARNINGS}- No code exploration detected. Before making changes:\n"
  WARNINGS="${WARNINGS}    * Read relevant source files to understand existing code\n"
  WARNINGS="${WARNINGS}    * Use claude-context MCP to semantically search the codebase\n"
  WARNINGS="${WARNINGS}    * Use cclsp MCP for go-to-definition and find-references across services\n"
  WARNINGS="${WARNINGS}    * Check claude-context memory for past architectural decisions\n"
fi

# Check for plan (TaskCreate marker within last 4 hours)
PLAN_MARKER="$MARKER_DIR/planned"
if [ ! -f "$PLAN_MARKER" ] || [ -z "$(find "$PLAN_MARKER" -mmin -240 2>/dev/null)" ]; then
  WARNINGS="${WARNINGS}- No task plan detected. Before implementing:\n"
  WARNINGS="${WARNINGS}    * Use TaskCreate to outline your approach\n"
  WARNINGS="${WARNINGS}    * Store key decisions in claude-context memory for future reference\n"
fi

if [ -n "$WARNINGS" ]; then
  echo "SESSION REMINDER:" >&2
  echo -e "$WARNINGS" >&2
  echo "Explore the code and create a plan before making changes to ensure quality." >&2
  touch "$WARNED_MARKER"
fi

exit 0
Changes

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.

  1. 8d ago First seen · 69 lines · 15 tokens per session scan A 0fb13579a24f

Subscribe to this mod's changes

hf.enforce-plan-and-explore is a skill published in the GitHub repository T-rav/hydraflow (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 15 tokens to every session and 710 once invoked, about $0.0001 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 2026-08-31.

Related

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.

jsmastery-pro/skills · 71 tokens

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…

jsmastery-pro/skills · 73 tokens

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.

jsmastery-pro/skills · 65 tokens

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.

jsmastery-pro/skills · 74 tokens

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…

jsmastery-pro/skills · 74 tokens

architect

Run /architect when choosing between approaches, designing a feature or page, picking a tech stack, or when /develop says a decision is owed, anytime a load bearing technical decision is unmade. Asks deep questions, recommends an answer, and writes a build spec to docs/specs/. Owns all spec files.

jsmastery-pro/skills · 66 tokens