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.
git clone --depth 1 https://github.com/SaigonXIII/evcWrote 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/saigonxiii/evc/reply-monitor)<a href="https://agentmods.dev/commands/saigonxiii/evc/reply-monitor"><img src="https://agentmods.dev/badge/commands/saigonxiii/evc/reply-monitor/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/commands/saigonxiii/evc/reply-monitor"><img src="https://agentmods.dev/badge/commands/saigonxiii/evc/reply-monitor.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 | $0.00000 | $0.00838 |
| Opus 5 | $0.00000 | $0.00419 |
| Sonnet 5 | $0.00000 | $0.00168 |
| Haiku 4.5 | $0.00000 | $0.00084 |
Grade A, and why
reply-monitor 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl "https://api.x.com/2/tweets/search/recent?query={{SOCIAL_HANDLE_X}} -from:{{SOCIAL_HANDLE_X_BARE}}&max_results=20&tweet.fields=author_id,created_at,in_reply_to_user_id,conversation_id,public_metrics&expansions=autho How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reply Monitor
Scan {{SOCIAL_HANDLE_X}} mentions, draft canon-aligned replies, and post approved responses. Also auto-replies with {{WEBSITE_URL}} link on own posts.
Trigger
User invokes /reply-monitor or says "check replies", "engagement check", "reply to mentions", "reply guy mode"
Steps
1. Pull Recent Mentions
source config/x-api.env
# Search for mentions in last 24h (or since last check)
curl "https://api.x.com/2/tweets/search/recent?query={{SOCIAL_HANDLE_X}} -from:{{SOCIAL_HANDLE_X_BARE}}&max_results=20&tweet.fields=author_id,created_at,in_reply_to_user_id,conversation_id,public_metrics&expansions=author_id&user.fields=username,name"
2. Classify Each Mention
For each mention, classify as:
- Question — asking about {{COMPANY_NAME}}, how it works, pricing, integration
- Positive — complimenting, agreeing, sharing enthusiasm
- Discussion — making a point about a relevant topic that we can build on
- Spam/Bot — irrelevant, engagement farming, spam
- Already replied — check if we've already responded in the thread
Skip spam/bot and already-replied.
3. Draft Replies
For each real mention, draft a reply following these rules:
Tone:
- Confident, not defensive
- Short — 1-2 sentences max, ideally under 200 chars
- Match the energy of the original (casual reply to casual mention, precise reply to technical question)
- Never sound like a brand bot — sound like a founder
Canon guardrails:
- Infrastructure positioning, not consumer framing
- Use approved language from brand canon
- Reference specific USPs when relevant
- Never make claims not in the canon
Reply patterns:
- Questions -> answer directly, end with {{WEBSITE_URL}} link if relevant
- Positive mentions -> acknowledge + add one insight they didn't mention
- Discussion -> agree with their point + connect to {{COMPANY_NAME}}'s angle
- Never argue or correct aggressively
4. Present for Approval
Show all draft replies in a table:
| # | Mention (excerpt) | Author | Draft Reply | Action |
|---|---|---|---|---|
| 1 | "where does simplicity..." | @user | "That's the point -- brands integrate once..." | Reply? |
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.
- 11d ago First seen · 100 lines · 0 tokens per session scan A ab3b094dd48a
reply-monitor is a command published in the GitHub repository SaigonXIII/evc (57 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 838 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
review-tool
Research a tool or product for skill-gap, architecture, and verb-fit per the Anatomy framework.
setup
First-run setup — replace the fictional company and authors with yours.
voice-check
Check a draft against the author's voice profile and flag deviations.
content-status
Scan all content directories and report status of drafts, ideas, and published content.
draft-blog
Scaffold a blog post with proper structure, voice, and frontmatter.
review-content
Review content for brand alignment, lead placement, bio consistency, and proof points.