What is hf.block-destructive-git?

A pre-tool safety check for shell commands that blocks several destructive Git operations. These include force-pushing, hard resets, restoring all files, deleting untracked files, and force-deleting branches.

For protecting repositories from high-risk Git commands during coding-agent sessions.

It prevents commands that can overwrite history or discard work before the user explicitly approves them.

How T-rav/hydraflow configures Claude Code and Codex

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.block-destructive-git/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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/t-rav/hydraflow/hf.block-destructive-git/github.svg)](https://agentmods.dev/skills/t-rav/hydraflow/hf.block-destructive-git)

Your own site

<a href="https://agentmods.dev/skills/t-rav/hydraflow/hf.block-destructive-git"><img src="https://agentmods.dev/badge/skills/t-rav/hydraflow/hf.block-destructive-git/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/t-rav/hydraflow/hf.block-destructive-git"><img src="https://agentmods.dev/badge/skills/t-rav/hydraflow/hf.block-destructive-git.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 379 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.

Model	Per session	Once invoked
Fable 5.1	$0.00013	$0.00379
Opus 5.5	$0.00005	$0.00152
Sonnet 5.5	$0.00003	$0.00076
Haiku 4.5	$0.00001	$0.00038

Measured 1mo ago against content hash 4fe0c54910c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hf.block-destructive-git 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 1mo 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.block-destructive-git/SKILL.md · 39 lines

What it actually says

hf.block-destructive-git

#!/bin/bash
# Hook: Block destructive git commands that are hard to reverse.
# Fires on PreToolUse for all Bash commands.
# Blocks: push --force, reset --hard, checkout ., restore ., clean -f, branch -D

set -euo pipefail

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

if [ -z "$COMMAND" ]; then
  exit 0
fi

# Block destructive git commands
if echo "$COMMAND" | grep -qE 'git\s+(push\s+.*--force|push\s+-f\b|reset\s+--hard|checkout\s+\.|restore\s+\.|clean\s+-f|branch\s+-D)'; then
  echo "BLOCKED: Destructive git command detected." >&2
  echo "" >&2
  echo "The following are forbidden without explicit user approval:" >&2
  echo "  - git push --force / -f  (overwrites remote history)" >&2
  echo "  - git reset --hard       (discards uncommitted changes)" >&2
  echo "  - git checkout .         (discards all working tree changes)" >&2
  echo "  - git restore .          (discards all working tree changes)" >&2
  echo "  - git clean -f           (deletes untracked files)" >&2
  echo "  - git branch -D          (force-deletes branch)" >&2
  echo "" >&2
  echo "Ask the user for explicit approval before running destructive commands." >&2
  exit 2
fi

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.

1mo ago First seen · 39 lines · 13 tokens per session scan A 4fe0c54910c9

Subscribe to this mod's changes

hf.block-destructive-git 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 379 once invoked, about $0.0001 per session on Opus 5.5. 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.

Git and workflow agentic-development agentic-workflow wishful-programming

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

feedback-resolution

Address PR review feedback through surgical fixes traceable to specific comments, apply the Boy Scout Rule only to already-modified files (separate improve: commits), recover context by code snippet rather than line number, and enforce pushback only when factually incorrect, test-breaking, or CLAUDE.md-violating. Use…

synaptiai/synapti-marketplace · 103 tokens

merge-and-release

Reference document describing merge prerequisites (approval, CI checks, mergeable, conversations resolved, stale approval), release versioning (semantic semver), and changelog generation. Explains why Tier 3 confirmation is structural: merge and release cost is borne by downstream people. Reference only…

synaptiai/synapti-marketplace · 82 tokens

merge-conflict-resolution

Detect, classify (porcelain status; complexity: trivial, semantic, structural, delete-modify), and resolve git merge conflicts through per-file strategy selection (accept-ours, accept-theirs, manual-merge, rebase), manual conflict hunk parsing, and post-resolution verification (orphaned markers, build, tests). Use…

synaptiai/synapti-marketplace · 114 tokens

branch-and-task-management

Create feature branches with naming conventions, load full issue context and impact analysis, and decompose acceptance criteria into atomic parallel tasks with dependencies. Use when starting work on a GitHub issue. This skill MUST be consulted because starting code without context causes misaligned implementations…

synaptiai/synapti-marketplace · 60 tokens

change-classification

Classify code changes as in-context, uncertain, or out-of-context using primary signals (branch diff, issue keywords, active tasks), secondary signals (directory proximity, test naming), and red-flag patterns (secrets, large binaries). Use when preparing commits or reviewing staged changes. This skill MUST be…

synaptiai/synapti-marketplace · 86 tokens

hydraflow: Skill for Claude Code