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 randommonicle/claude-skills --skill blast-radius-grepgit clone --depth 1 https://github.com/randommonicle/claude-skillsWrote 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/randommonicle/claude-skills/blast-radius-grep)<a href="https://agentmods.dev/skills/randommonicle/claude-skills/blast-radius-grep"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/blast-radius-grep/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/randommonicle/claude-skills/blast-radius-grep"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/blast-radius-grep.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 | $0.00167 | $0.00785 |
| Opus 5 | $0.00084 | $0.00392 |
| Sonnet 5 | $0.00033 | $0.00157 |
| Haiku 4.5 | $0.00017 | $0.00078 |
Grade A, and why
blast-radius-grep 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blast-radius grep
Converged independently in all three mined repos: the named list of places to change under-counts, whether the thing changed is a code action or a duplicated fact. A spec named two receipt-posting sites and the grep found the third; a corrected marketing claim was fixed in the chat prompt and lived on in two site pages and a trust stat; a new gate's "low effort" estimate omitted the corpus of existing writes that now failed it.
The rule
Before shipping the change, enumerate by grep, not by list. Grep the ACTION (the verb on the table, the dropped column's name, the gated write) or the FACT (the old value and its paraphrases) across: app code, tests, seeds, scripts, open branches, and the built or rendered output. Fix every occurrence in the same pass — the corpus is part of the change's real cost.
How to apply
- Grep by the thing changed, not the feature name. A governed-set migration broke an untouched smoke because the sweep searched the feature, not the changed set.
- Constraints reconcile against fixtures, not only live data. A new CHECK that live rows satisfy can still strand test payloads red for weeks.
- Drops and renames grep unmerged branches and test payloads too — the next merge re-introduces the name you removed.
- Facts: grep the rendered output as well as source. The built site carried a claim the source grep missed; "grep the built site, not just chat.js".
- Then prevent re-divergence. Leave a single-source anchor (shared config, one exported constant). For a value denormalised into a second store, back the copy with a trigger — not a convention — and ship a standing "these two must match / zero rows" drift-check query, used as both post-change verification and future diagnosis. An insert-time-only email sync once mis-routed a client's reports for weeks.
What this skill does not do
It does not verify references in documents — verified-citations owns whether a cited file:line or date is accurate; this skill owns whether a duplicated value was fixed everywhere. It does not decide the change itself (plan-first routes here).
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.
- 11d ago First seen · 50 lines · 167 tokens per session scan A cd4ba53d90a1
blast-radius-grep is a skill published in the GitHub repository randommonicle/claude-skills (23 stars, last pushed 4d ago), licensed Apache-2.0. It adds 167 tokens to every session and 785 once invoked, about $0.0008 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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…