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 commands/ivanlutsenko/awac-ai-agent-plugins/install-permissionsgit clone --depth 1 https://github.com/IvanLutsenko/awac-ai-agent-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/commands/ivanlutsenko/awac-ai-agent-plugins/install-permissions)<a href="https://agentmods.dev/commands/ivanlutsenko/awac-ai-agent-plugins/install-permissions"><img src="https://agentmods.dev/badge/commands/ivanlutsenko/awac-ai-agent-plugins/install-permissions.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 | $0.00026 | $0.01484 |
| Opus 5 | $0.00013 | $0.00742 |
| Sonnet 5 | $0.00005 | $0.00297 |
| Haiku 4.5 | $0.00003 | $0.00148 |
Grade B, and why
install-permissions scanned grade B 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 4d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- label: "User-level (~/.claude/settings.json)" How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install Crashlytics permissions
Adds the Crashlytics plugin's read-only Bash and MCP tools to your settings.json
allowlist so /crashlytics:crash-report runs without permission prompts.
What gets added — strictly read-only operations:
- git:
status,log,blame,diff,show,fetch,branch,remote,ls-tree,ls-files,rev-parse,merge-base - crashlytics scripts (validate-report.py, fetch-crash-data.py, check-prerequisites.sh)
- MCP read tools:
crashlytics_get_*,crashlytics_list_*,crashlytics_batch_get_events,crashlytics_get_report,firebase_get_*,firebase_list_*
What is NEVER added — write/auth/destructive operations:
git push,git commit,git reset,git rebase,git cleancrashlytics_update_issue,crashlytics_create_note,crashlytics_delete_notefirebase_login,firebase_logout,firestore_*,auth_*,storage_*,messaging_*,realtimedatabase_*,remoteconfig_*
Step 1: Choose scope
AskUserQuestion:
questions:
- question: "Where to install the allowlist?"
header: "Scope"
options:
- label: "User-level (~/.claude/settings.json)"
description: "Applies in every project. Recommended if you use the plugin in multiple repos."
- label: "Project-level (.claude/settings.local.json)"
description: "Only this project. Safer if you don't want global allowance."
multiSelect: false
If User-level → SETTINGS_PATH = ~/.claude/settings.json.
If Project-level → SETTINGS_PATH = .claude/settings.local.json (mkdir -p .claude if missing).
Step 2: Read current settings
Bash: test -f {SETTINGS_PATH} && echo EXISTS || echo NEW
Read tool: {SETTINGS_PATH} # if EXISTS
If NEW:
CURRENT = { "permissions": { "allow": [] } }
Else:
CURRENT = <parsed JSON>
Ensure permissions.allow exists, default to []
Step 3: Compute the diff
SAFE_SET = [
# git read-only
"Bash(git status:*)",
"Bash(git log:*)",
"Bash(git blame:*)",
"Bash(git diff:*)",
"Bash(git show:*)",
"Bash(git fetch:*)",
"Bash(git ls-tree:*)",
"Bash(git ls-files:*)",
"Bash(git rev-parse:*)",
"Bash(git merge-base:*)",
"Bash(git branch:*)",
"Bash(git remote:*)",
"Bash(git config --get:*)",
# crashlytics scripts
"Bash(${CLAUDE_PLUGIN_ROOT}/scripts/check-prerequisites.sh:*)",
"Bash(python3 ${CLAUDE_PLUGIN_ROOT}/scripts/validate-report.py:*)",
"Bash(python3 ${CLAUDE_PLUGIN_ROOT}/scripts/fetch-crash-data.py:*)",
# generic safe utils used by the plugin
"Bash(test -f:*)",
"Bash(touch .claude/crashlytics-prereqs-ok)",
# MCP — read-only Crashlytics
"mcp__plugin_crashlytics_firebase__crashlytics_get_issue",
"mcp__plugin_crashlytics_firebase__crashlytics_batch_get_events",
"mcp__plugin_crashlytics_firebase__crashlytics_list_events",
"mcp__plugin_crashlytics_firebase__crashlytics_get_report",
"mcp__plugin_crashlytics_firebase__crashlytics_list_notes",
# MCP — read-only Firebase project info
"mcp__plugin_crashlytics_firebase__firebase_get_environment",
"mcp__plugin_crashlytics_firebase__firebase_list_apps",
"mcp__plugin_crashlytics_firebase__firebase_get_project",
"mcp__plugin_crashlytics_firebase__firebase_list_projects",
"mcp__plugin_crashlytics_firebase__firebase_get_sdk_config",
]
EXISTING = set(CURRENT["permissions"]["allow"])
TO_ADD = [r for r in SAFE_SET if r not in EXISTING]
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.
- 4d ago First seen · 167 lines · 26 tokens per session scan B b3579e15710e
install-permissions is a command published in the GitHub repository IvanLutsenko/awac-ai-agent-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 1,484 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.