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.diff-sanity/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.diff-sanity)<a href="https://agentmods.dev/skills/t-rav/hydraflow/hf.diff-sanity"><img src="https://agentmods.dev/badge/skills/t-rav/hydraflow/hf.diff-sanity/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.
<a href="https://agentmods.dev/skills/t-rav/hydraflow/hf.diff-sanity"><img src="https://agentmods.dev/badge/skills/t-rav/hydraflow/hf.diff-sanity.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00026 | $0.00443 |
| Opus 5.5 | $0.00010 | $0.00177 |
| Sonnet 5.5 | $0.00005 | $0.00089 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
hf.diff-sanity 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.
What it actually says
Diff Sanity Check
Review the current branch diff for common implementation mistakes before committing. This is a read-only check — it does not modify files.
When to Use
- After implementing changes, before committing
- As a pre-review sanity pass
- When you want a quick check for accidental mistakes
Instructions
-
Get the diff of changes on the current branch:
git diff origin/main...HEADIf that's empty, fall back to
git diff(unstaged) orgit diff --cached(staged). -
Review the diff for these problems:
- Accidental deletions — unrelated code removed that should not have been
- Leftover debug code —
print(),console.log(),debugger,breakpoint(), commented-out code - Missing imports — new symbols referenced but not imported; removed code with stale imports
- Scope creep — files changed that are unrelated to the issue
- Hardcoded secrets or credentials — API keys, tokens, passwords in the diff
- Broken string literals — unclosed quotes, malformed f-strings
- Obvious logic errors — inverted conditions, off-by-one, unreachable code after return
-
For each problem found, note the file path, line, and description.
-
Produce structured output:
If all checks pass:
DIFF_SANITY_RESULT: OK
SUMMARY: No issues found
If problems are found:
DIFF_SANITY_RESULT: RETRY
SUMMARY: <comma-separated list of problem categories found>
FINDINGS:
- <file:line — description>
Important
- Do NOT modify any files. This is a read-only review.
- Focus on objective mistakes, not style preferences.
- If the diff is too large (>15,000 chars), summarize by file and focus on the riskiest 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 · 57 lines · 26 tokens per session scan A c9c513957672
hf.diff-sanity is a skill published in the GitHub repository T-rav/hydraflow (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 26 tokens to every session and 443 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.
Other skills, from other repositories
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…
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…
holdout-validation
Cross-reference agent self-review claims and evidence-bundle entries against actual file state using hidden holdout scenarios, producing P1/P2/P3 findings mapped to visible acceptance criteria only. Checks that every expected value in the tests has the source the bundle claims and that every risk-map row has a…
code-quality-principles
Enforce code quality through the Boy Scout Rule (leave code better than found), secret-free commits, production-ready code (no TODOs, console.log, mocks, or commented code), and self-review against an atomic-commits checklist. Use when writing, modifying, or reviewing code. This skill MUST be consulted because…
code-review-methodology
Conduct two-stage code review: Stage 1 verifies spec compliance (criterion-to-code mapping), Stage 2 evaluates security, correctness, performance, and maintainability across 6 parallel facets with P1/P2/P3 synthesis and deduplication by file:line. For the Tests facet the reviewer derives expected behavior from the…
pr-lifecycle
Reference document describing PR lifecycle: pre-flight gates (4 conditions), verification gate (5 conditions), body structure (from templates/pr-body.md), reviewer-suggestion algorithm (CODEOWNERS → file expertise → recent activity → workload balance), and finding-ledger merge prerequisite. Reference only (policy…