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 terrylica/cc-skills --skill tcc-grant-auditgit clone --depth 1 https://github.com/terrylica/cc-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/terrylica/cc-skills/tcc-grant-audit)<a href="https://agentmods.dev/skills/terrylica/cc-skills/tcc-grant-audit"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/tcc-grant-audit/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/terrylica/cc-skills/tcc-grant-audit"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/tcc-grant-audit.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 | $0.00186 | $0.02051 |
| Opus 5.5 | $0.00074 | $0.00820 |
| Sonnet 5.5 | $0.00037 | $0.00410 |
| Haiku 4.5 | $0.00019 | $0.00205 |
Grade A, and why
tcc-grant-audit scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 25d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| Watch grants change live | `sudo eslogger tcc_modify` | Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tcc-grant-audit — macOS privacy grants, all stores
Self-Evolving skill — every rule below was MEASURED, not inferred. If a macOS release changes one, fix this file and the scripts; see Post-Execution Reflection.
Resolve the scripts against the version Claude Code actually loaded:
SKILL="$(cc-plugin-root macos-permissions)/skills/tcc-grant-audit"
Start here, always
bash "$SKILL/tcc-audit.sh" all # READ-ONLY. Changes nothing.
🔴 The seven things that will bite you
1. tccutil is not the only tool, and is the wrong one for half the job. Reach for the whole set:
| Need | Tool |
|---|---|
| Query any grant, any service, any store | sqlite3 -readonly on TCC.db |
| Is this bundle id still installed? | NSWorkspace via osascript -l JavaScript (one line) |
| What does a grant actually pin? | /usr/bin/csreq -r- -t |
| Watch grants change live | sudo eslogger tcc_modify |
| Ground truth on whether a write landed | log show --predicate 'subsystem == "com.apple.TCC"' |
| Reset a grant for an INSTALLED app | /usr/bin/tccutil reset <Service> <id> |
| Clear a grant for an UNINSTALLED app | tcc-clear-orphans.sh (stub technique) |
Remove a client_type=1 path row |
a direct DB writer, user store only |
2. Order is load-bearing: reset the grant BEFORE deleting the app. tccutil resolves the identifier through LaunchServices first. Delete the app and every reset fails -10814 forever.
3. tccutil reports success on a no-op. It prints Successfully reset and exits 0 while deleting nothing. Verify every change with SELECT COUNT(*) against the database. Third-party tools do this too — a direct DB writer exits 0 when the write was refused.
What ships with it
3 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.
- 25d ago First seen · 114 lines · 186 tokens per session scan A 2b49c7bd899e
tcc-grant-audit is a skill published in the GitHub repository terrylica/cc-skills (0 stars, last pushed today), licensed MIT. It adds 186 tokens to every session and 2,051 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-21.
Other skills, from other repositories
example-feature-generator
Generate boilerplate for new features following project conventions. Use when user says "create feature", "add feature", or "new feature scaffolding".
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
thinking-theory-of-constraints
When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.
authentication-patterns
OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns.
agent-flutter-developer
Specialist subagent: Flutter/Dart cross-platform development, Riverpod state management, and platform channels specialist. Use when building Flutter apps, implementing state management, or working with native platform features. Trigger phrases: Flutter, Dart, Riverpod, Bloc, widget, MaterialApp, GoRouter, platform…
content-repurposer
Adapt content across platforms with tone/format shifting — blog to social, long to short, text to visual outline. Use when repurposing content for different channels, audiences, or formats.