tell-proof: Command for Claude Code

.cursor/commands/semantic-commits.md

semantic-commits is a command for Claude Code, Cursor from ashishpatill/tell-proof. It costs 0 tokens per session (535 once invoked), scanned A, original, MIT.

A command for splitting a branch's work into small Conventional Commits and pushing the result. Conventional Commits use prefixes such as feat, fix, docs, and test to describe each change.

In plain words
What is it for?
Use it to inspect uncommitted work, create focused buildable commits, update a pull request after rewriting history, and push the branch.
Why use it?
It makes a mixed or squashed change history easier to review and understand. The rules keep unrelated changes separate and avoid vague commit messages.

Command for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code command (commands/*.md).

This is ashishpatill/tell-proof's own configuration. It tells Claude Code and Cursor how to work on tell-proof 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 tell-proof configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ashishpatill/tell-proof. 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/ashishpatill/tell-proof/master/.cursor/commands/semantic-commits.md
Clone the repo
git clone --depth 1 https://github.com/ashishpatill/tell-proof

Made for: Claude Code, Cursor.

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 semantic-commits

README.md
[![agentmods](https://agentmods.dev/badge/commands/ashishpatill/tell-proof/semantic-commits/github.svg)](https://agentmods.dev/commands/ashishpatill/tell-proof/semantic-commits)
Your own site
<a href="https://agentmods.dev/commands/ashishpatill/tell-proof/semantic-commits"><img src="https://agentmods.dev/badge/commands/ashishpatill/tell-proof/semantic-commits/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 semantic-commits

Your own site · 80×15
<a href="https://agentmods.dev/commands/ashishpatill/tell-proof/semantic-commits"><img src="https://agentmods.dev/badge/commands/ashishpatill/tell-proof/semantic-commits.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 535 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 $0.00000 $0.00535
Opus 5.5 $0.00000 $0.00214
Sonnet 5.5 $0.00000 $0.00107
Haiku 4.5 $0.00000 $0.00053

Measured 1mo ago against content hash d271c0437e41, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

semantic-commits 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.

.cursor/commands/semantic-commits.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Semantic commits

Rewrite the current branch's uncommitted (or single squashable) work into as many small conventional commits as possible, then push.

Rules

  1. Use conventional commit subjects only: feat|fix|docs|test|chore|ci|refactor|perf|build(scope): …
  2. Never mention Cursor, cloud agents, Copilot, or similar tooling in commit messages or PR text.
  3. One logical change per commit — prefer more commits over fewer. Good splits:
    • schema contracts alone
    • one detector or pure function
    • one capture/helper module
    • one fixture file
    • tests for one area
    • one script or CI wire-up
    • docs/tracker updates last (or per doc file)
  4. Do not squash unrelated packages into one commit.
  5. Keep commits buildable when practical; if an intermediate commit must be incomplete, keep follow-ups tight and sequential.
  6. Prefer git add of specific paths over git add -A.
  7. After all commits: git push -u origin <branch> (force-with-lease only when rewriting already-pushed commits on this feature branch).
  8. Update the open PR description if history was rewritten — still no tooling brand names.

Procedure

  1. Inspect git status and git diff --stat against the merge base (master unless told otherwise).
  2. If work is already one fat commit on the feature branch: git reset --soft <base> then unstage (git reset HEAD) so files are working-tree changes.
  3. Group files into the smallest coherent commits; commit each with a precise message.
  4. Run pnpm test (and schema build / web typecheck if schema or web changed) before the final push when feasible.
  5. Push the branch.
  6. Reply with the commit list (git log --oneline <base>..HEAD) and the remote branch tip.

Message style examples

feat(schema): add ScenarioMatrix and ProofMatrixResult contracts
feat(core): detect ResponsiveViewportDrift on viewport collapse
feat(corpus): add marketplace-clutter live-site capture
test(core): golden-assert scenario matrix self-compare
ci: smoke proof matrix on UI pull requests
docs: mark Phase 5 scenario matrix as shipped
chore: ignore proof matrix CI artifact

Read the full file on GitHub · 47 lines

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. 1mo ago First seen · 47 lines · 0 tokens per session scan A d271c0437e41

Subscribe to this mod's changes

semantic-commits is a command published in the GitHub repository ashishpatill/tell-proof (2 stars, last pushed 22d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 535 tokens. 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.