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 agentmods add skills/apurvbazari/claude-plugins/checknpx skills add ApurvBazari/claude-plugins --skill checkgit clone --depth 1 https://github.com/ApurvBazari/claude-pluginsWrote 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/apurvbazari/claude-plugins/check)<a href="https://agentmods.dev/skills/apurvbazari/claude-plugins/check"><img src="https://agentmods.dev/badge/skills/apurvbazari/claude-plugins/check.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 | $0.00082 | $0.01185 |
| Opus 5 | $0.00041 | $0.00593 |
| Sonnet 5 | $0.00016 | $0.00237 |
| Haiku 4.5 | $0.00008 | $0.00119 |
Grade D, and why
check scanned grade D with 2 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 3d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
- **Cwd mismatch is informational, not fatal** — surface it but don't refuse to report. Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
If the body is longer than 12 lines, append "*(truncated — run `cat .claude/handoff/active.md` for the full directive)*". How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check Skill — Handoff Health Check
You are running a read-only health check for the handoff plugin in the current project. No files are modified.
Step 1: Check for an active handoff
Look for .claude/handoff/active.md. Two paths:
No file present
Report:
No active handoff in this project.
- Save one with
/handoff:saveor by saying "save handoff" / "pick this up later".- Settings file:
<exists | absent>at.claude/handoff/settings.md.
If .claude/handoff/settings.md exists, mention it; otherwise note "no settings file → defaults apply".
File present
Parse the frontmatter and compute progress signals.
Step 2: Compute progress signals
# Eval-safety (audit finding M2): compute-progress.sh emits every value via
# `printf '%q'`, so re-evaluation here cannot perform command substitution even
# when a field (e.g. retention_value) is read from caller-controlled settings.md
# frontmatter. The contract is regression-pinned by tests/handoff/test_compute_progress.sh,
# whose adversarial canary cases assert injected `$(...)`/backticks do NOT execute.
eval "$(bash "${CLAUDE_PLUGIN_ROOT}/scripts/compute-progress.sh" "$(pwd)")"
# Exports: days_old, current_branch, commits_past, cwd_match,
# snooze_remaining, archive_count, retention_value
The helper always exits 0; missing values emit as unknown. Also read
stale-commit-threshold and stale-day-threshold from
.claude/handoff/settings.md for the Step 3 report (configuration, not
computed signals).
Step 3: Report
Present a structured report (markdown table, single block):
Handoff status —
.claude/handoff/active.mdis active
Field Value Saved at <saved-at>(<days-old>days ago)Saved-at SHA <short-sha>Saved-at branch <branch>Saved-from cwd <path>Current cwd <pwd>(`<matchCurrent branch <branch>Commits past saved-at <n>Snooze <status>Settings file `<exists Archive retention <value>(default 10)Archive count <n>files in.claude/handoff/archive/Will surface at next SessionStart?
<yes | no — reason>
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.
- 3d ago First seen · 109 lines · 82 tokens per session scan D 588913381095
check is a skill published in the GitHub repository ApurvBazari/claude-plugins (0 stars, last pushed 27d ago), licensed MIT. It adds 82 tokens to every session and 1,185 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it D with 2 findings (tells the agent never to refuse, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
cross-platform
Cross-platform development patterns for macOS, Windows, and Linux.
shell-scripting
Shell scripting best practices for cross-platform CLI tools.
c-notify
Send native macOS notification center alerts from the command line using terminal-notifier.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.