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/asysta-act/agent-flow/check-setupnpx skills add asysta-act/agent-flow --skill check-setupgit clone --depth 1 https://github.com/asysta-act/agent-flowWhat 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 | $0.00013 | $0.04747 |
| Opus 5 | $0.00006 | $0.02374 |
| Sonnet 5 | $0.00003 | $0.00949 |
| Haiku 4.5 | $0.00001 | $0.00475 |
Grade B, and why
check-setup scanned grade B with 2 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 2d 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.
b. Check whether `~/.claude/settings.json` contains a PostToolUse hook entry referencing `validate-dispatch`. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Run a curl probe to confirm network reachability: How it starts
The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check Setup
Check the project configuration for the agent-flow pipeline. Report: what works, what is missing, what failed.
If $ARGUMENTS contains --skip-build, skip running build/test commands.
Steps
Block 1: Automation Config (structural check)
- Read the current project's CLAUDE.md
- Verify the existence of the
## Automation Configsection → [OK] or [FAIL] - Verify required sections and keys:
| Section | Required keys |
|---|---|
| Issue Tracker | Type (or default youtrack), Instance, Project, Bug query, State transitions, On start set |
| Source Control | Remote, Base branch, Branch naming |
| PR Rules | Labels (Title format optional) |
| PR Description Template | (subsection present) |
| Build & Test | Build command, Test command |
3a. Per-tracker validation
Path note:
trackers.mdlives in the plugin installation directory, not in the consuming project. Glob is used to handle CWD-context mismatch.
Locate trackers.md: Glob with pattern .claude/plugins/**/docs/reference/trackers.md first.
If no results, Glob with **/docs/reference/trackers.md. If still none, try docs/reference/trackers.md relative to CWD.
If multiple results, prefer the path containing .claude/plugins/ or agent-flow/; if ambiguous → [WARN] "Multiple trackers.md found — using {path}."
If the file cannot be found → [WARN] "trackers.md not found — per-tracker validation skipped. Verify plugin installation." and skip the rest of Step 3a.
Find the row matching the configured Type in the Validation Rules table.
- Apply the query validation rule for that tracker to the Bug query value
- Apply the state transition format check to the State transitions value
- Apply the instance validation rule (if any) to the Instance value
- For unknown Type → [WARN] "Unknown tracker type '{Type}'. Validation skipped."
- For each key: verify that the value exists and is NOT a placeholder (
<...>)- Present and filled → [OK]
- Empty or placeholder → [FAIL]
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.
- 2d ago First seen · 310 lines · 13 tokens per session scan B ee41ea3f464a
check-setup is a skill published in the GitHub repository asysta-act/agent-flow (12 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 4,747 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
team-up
Orchestrate persistent agent teams with TeamCreate. Use when the user says "team up", "spin up a team", or invokes /team-up.
cortivex-pipeline
Build and run AI agent pipelines that decompose complex tasks into coordinated agent workflows.
project-graveyard
Scans the developer's machine for dead side projects, autopsies each one from its git history (died at the payments wall, killed by a newer project, finished but never shipped), surfaces their personal death patterns, and picks the corpse most worth resurrecting — then helps ship it. Use when the user mentions…
web-app-penetration-testing
Pentest a web app or website end to end — black-box testing of a live URL, staging environment, or local dev server that finds and exploits real vulnerabilities (auth bypass, broken access control, IDOR, injection, XSS, SSRF, business logic) and proves each one with a working proof-of-concept instead of a signature…
haiku
When writing a haiku for this bot, follow these conventions.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…