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 skills add Kpoiut/ruleblast --skill discoverygit clone --depth 1 https://github.com/Kpoiut/ruleblastWrote 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/kpoiut/ruleblast/discovery)<a href="https://agentmods.dev/skills/kpoiut/ruleblast/discovery"><img src="https://agentmods.dev/badge/skills/kpoiut/ruleblast/discovery.svg" alt="Measured on agentmods" 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 | $0.00053 | $0.01371 |
| Opus 5 | $0.00026 | $0.00685 |
| Sonnet 5 | $0.00011 | $0.00274 |
| Haiku 4.5 | $0.00005 | $0.00137 |
Grade A, and why
ruleblast 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 6d 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.
This is a copy
100% identical to ruleblast — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RuleBlast — Git diff for AI agent repository instructions
Local, read-only Git CLI. No network or model call during analysis.
You cannot see which agent inherited an AGENTS.md / CLAUDE.md edit without this scoreboard. Git will not show that second diff.
Permission
Default is ask. Do not run npx or ruleblast until the human says yes.
The human turns the gate on without us writing files:
- env
RULEBLAST_AGENT_ALLOW=yes, or - a user-created
.ruleblast-allowcontainingyes
Turn it off with RULEBLAST_AGENT_ALLOW=off or by deleting / setting that file to off. After allow is yes, you may run the four routes below. npx still writes the npm cache — mention that when you ask.
There is no ruleblast scan subcommand. diff has no --from.
Discovery
Same skill body at every official path. Not discovered from node_modules.
- Codex CLI / ChatGPT desktop / Codex IDE:
.agents/skills/ruleblast/SKILL.md— https://learn.chatgpt.com/codex/build-skills - Claude Code:
.claude/skills/ruleblast/SKILL.md— https://code.claude.com/docs/en/skills - Cursor:
.cursor/skills/ruleblast/SKILL.md— https://cursor.com/docs/skills - Windsurf Cascade:
.windsurf/skills/ruleblast/SKILL.md - Kiro:
.kiro/skills/ruleblast/SKILL.md— https://kiro.dev/docs/skills
VS Code-family companion: hosts/vscode. Same folder in VS Code, GitHub Copilot Chat, Cursor, Windsurf, Kiro, Antigravity, Codex IDE, Continue, Cline, Trae, VSCodium, Roo Code. Not a second engine. A host is not a modeled reality.
MCP stdio: ruleblast --mcp. Four tools: scan, diff, explain, case.
- Claude Code / Copilot Agent Host:
.mcp.json - GitHub Copilot in VS Code:
.vscode/mcp.json - Codex desktop / CLI / IDE:
.codex/config.toml - Cursor, Kiro, Antigravity, Continue: workspace MCP JSON next to this skill
- Claude Desktop, Cline, Zed, JetBrains AI Assistant, Visual Studio Copilot, Neovim, Windsurf Cascade, Roo Code: paste snippets in
discovery/
Routes
| Symptom | Command |
|---|---|
| What does each pinned CLI project now? | npx --yes [email protected] . --color=never |
| Which stacks moved? | npx --yes [email protected] diff HEAD~1 --to HEAD --color=never |
| Why this path? | npx --yes [email protected] explain <path> --from HEAD~1 --to HEAD --json |
| Teaching receipt, no clone | npx --yes [email protected] case --color=never |
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 67 lines · 53 tokens per session scan A 2396d7f8a347
ruleblast is a skill published in the GitHub repository Kpoiut/ruleblast (19 stars, last pushed 12d ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,371 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to ruleblast, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
setup-caliber
Sets up Caliber for automatic AI agent context sync. Installs pre-commit hooks so CLAUDE.md, Cursor rules, and Copilot instructions update automatically on every commit. Use when Caliber hooks are not yet installed or when the user asks about keeping agent configs in sync.
git-github-flow
Use for branch prep, clean commits, PR descriptions, GitHub issue triage, changelogs, release notes, review response, merge readiness, or publishing a branch safely.
bisect
Binary search for root cause: define a search space and a pass/fail oracle, then halve the space each step until the culprit commit, config key, or dependency is isolated. Works across git history, configuration, dependencies, or code modules.
git-flow
Use when committing, branching, opening PRs, or deciding merge/branch strategy.
commit
Smart conventional commit with security validation, branch flow enforcement, and auto-detection. Use when committing changes, saving work, staging and committing, or choosing a conventional commit message.
post-commit
Use when a code commit just landed (not wip/amend/undo) and CHANGELOG or plugin-version post-commit actions are needed.