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/nirholas/xactions/reputation-auditnpx skills add nirholas/XActions --skill reputation-auditgit clone --depth 1 https://github.com/nirholas/XActionsWrote 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/nirholas/xactions/reputation-audit)<a href="https://agentmods.dev/skills/nirholas/xactions/reputation-audit"><img src="https://agentmods.dev/badge/skills/nirholas/xactions/reputation-audit.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 | $0.00088 | $0.01349 |
| Opus 5 | $0.00044 | $0.00674 |
| Sonnet 5 | $0.00018 | $0.00270 |
| Haiku 4.5 | $0.00009 | $0.00135 |
Grade A, and why
reputation-audit 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 5d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reputation Audit
Scores your own posts against a risk rubric with one LLM call per post, then rolls
the verdicts into a 0-100 reputation score, a letter grade, and the specific posts
worth a second look. Three surfaces share one scoring engine
(src/ai/reputationScorer.js): a browser script that also renders a downloadable,
shareable score card image; a CLI command for scripting; and an API route for
agents.
This audits your own content for risk, not someone else's account and not follower quality. For follower/network audits, use Community Health Monitoring. For bulk-deleting by age, keyword, or engagement rather than AI-judged risk, use Content Cleanup.
The rubric
Every post is scored 0 (no risk) to 100 (severe) on up to four dimensions in a single model call, plus an optional custom question:
| Dimension | Question |
|---|---|
| 💼 Professional | Would this embarrass the author to an employer, client, or business partner? |
| ⚔️ Hostile | Is this a personal attack on someone named or identifiable? |
| ⚖️ Legal exposure | Defamation, doxxing, a threat, leaked confidential info, an unkeepable promise? |
| 🗑️ Low value | Low-effort spam or filler that adds nothing? |
The overall score for a post is the MAX across its dimensions, not the average:
one severe dimension and three clean ones is still a post worth flagging.
Verdict: flagged at 70+, review at 40-69, clean below 40
(FLAG_THRESHOLD / REVIEW_THRESHOLD in the scorer module).
The account-level reputation score blends the average risk across all scanned posts (60%) with the single worst post (40%), so one severe outlier still pulls the grade down even when everything else is clean.
The report carries dimensionAverages and dimensionPeaks side by side. Read
and present the peak, not just the average: one post at 92 among four clean ones
averages to 18, and reporting only that contradicts the grade the same report
gives.
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.
- 5d ago First seen · 123 lines · 88 tokens per session scan A a55640e28a38
reputation-audit is a skill published in the GitHub repository nirholas/XActions (509 stars, last pushed yesterday), licensed Apache-2.0. It adds 88 tokens to every session and 1,349 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
stripe-projects
Use after E2B sandbox/API access has been provisioned through Stripe Projects and the user needs to use the resulting E2B API key with the E2B CLI, JavaScript SDK, Python SDK, or Code Interpreter SDK.
tape-opens
Stack-unwind review of this conversation - a tree of main tasks done (struck through) and every open left behind at the depth it was abandoned, sized by the thread's measured shape, never by feel. Optional argument - a .jsonl path or session id to review a different session.
powerpoint
Create designed, editable PowerPoint .pptx presentations with PptxGenJS. Use when the user asks to create, generate, update, or inspect a deck, slide deck, presentation, or .pptx file.
bear-notes
Create, search, and manage Bear notes via grizzly CLI.
connect-agent
Connect the codebase's AI agent to LangWatch agent simulations, so test suites run against the real agent process. Adds a small connect function beside the service startup that calls the agent already in the codebase, which opens an outbound connection and registers the agent with its environment and its run…
clawhub
Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI.