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 flonat/flonat-research --skill sync-permissionsgit clone --depth 1 https://github.com/flonat/flonat-researchWrote 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/flonat/flonat-research/sync-permissions)<a href="https://agentmods.dev/skills/flonat/flonat-research/sync-permissions"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/sync-permissions/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/flonat/flonat-research/sync-permissions"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/sync-permissions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 18 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 33 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 43 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 105 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Rogue Agent · line 46 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00054 | $0.00983 |
| Opus 5 | $0.00027 | $0.00491 |
| Sonnet 5 | $0.00011 | $0.00197 |
| Haiku 4.5 | $0.00005 | $0.00098 |
Grade B, and why
sync-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 8d 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.
- After adding new permissions to `~/.claude/settings.json` How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Rules Skill
Sync global permissions, skills, and agents into the current project without losing project-specific settings.
Purpose
The SessionStart hook only copies permissions when .claude/settings.local.json doesn't exist yet. After that, new global permissions never propagate to existing projects. This skill fills that gap — run it anytime to pull in new permissions additively.
When to Use
- After adding new permissions to
~/.claude/settings.json - When starting work in a project that hasn't been updated in a while
- After creating a new skill and wanting it available everywhere
- When the user says "sync permissions", "update rules", "update my permissions"
What It Does
- Merge permissions — adds global permissions into project-local, keeping any project-specific ones
- Verify skills directory — ensures
<skills-root>/exists and has content - Verify agents directory — ensures
~/.claude/agents/exists and has content - Report changes — shows exactly what was added
What It Does NOT Do
- Never removes existing project permissions (additive only)
- Never modifies
~/.claude/settings.json(reads it, never writes) - Never touches
model,hooks, or other global settings keys
Workflow
Step 1: Read Both Permission Files
Read these two files:
- Global:
~/.claude/settings.json→ extractpermissions.allowarray - Local:
.claude/settings.local.json→ extractpermissions.allowarray
If the local file doesn't exist, create it with global permissions (same as the SessionStart hook).
Step 2: Compute the Union
Merge the two permission arrays:
- Start with all existing local permissions (preserve everything)
- Add any global permissions not already present in local
- Sort the final array for readability
The merge logic:
new_permissions = local_permissions ∪ global_permissions
added = new_permissions - local_permissions
Step 3: Write the Merged Result
If there are new permissions to add:
- Read the full local settings file (preserve any non-permissions keys)
- Replace
permissions.allowwith the merged array - Write back to
.claude/settings.local.json
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.
- 8d ago First seen · 125 lines · 54 tokens per session scan B 1634ba5614ac
sync-permissions is a skill published in the GitHub repository flonat/flonat-research (133 stars, last pushed 17d ago), licensed MIT. It adds 54 tokens to every session and 983 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
fin-paper-convert
Compile LaTeX to PDF and convert to target journal format.
fin-paper-plan
Generate structured paper outline adapted to target journal.
doc-audit
Evaluate one project document in detail — a workbook section, big picture, strategy map, handoff message, paper, brief, or primer — without editing it. Runs the mechanical lint, builds a claim ledger, types every headline against the eight claim statuses in CLAUDE.md, traces cited evidence to the scripts and logs that…
latex-compile
Compile a LaTeX document and fix every error plus aesthetic issue (overfull/underfull boxes, widows, alignment, fonts) for a clean PDF and log. Use this instead of running pdflatex/latexmk manually — it avoids the latexmk stale-log trap and silent grep failures on binary log output, and it reformats rather than…
claim-audit
Audit what a passing script actually established, before writing any prose about it — build the computed-object ledger, rewrite every check's label as the weakest statement that makes its body pass, and separate the verdict on someone else's work from your own new claim. Run after the script passes and BEFORE the…
nb-to-wolfbook
Convert Mathematica .nb or .m files to Wolfbook .wb format so they open and run in VS Code. Use when bringing existing .nb/.m files into Wolfbook, or to make an existing .wb bridge-safe.