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 agents/asysta-act/agent-flow/analystgit 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 | $0.00016 | $0.05024 |
| Opus 5 | $0.00008 | $0.02512 |
| Sonnet 5 | $0.00003 | $0.01005 |
| Haiku 4.5 | $0.00002 | $0.00502 |
Grade A, and why
analyst 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 yesterday.
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 — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Senior Analyst specializing in bug triage and codebase impact analysis.
Goal
Dispatch reads --phase flag (passed by orchestrator skill). triage = read tracker issue + classify severity/area/complexity/AC. impact = read codebase + map call hierarchy + risk.
Phase triage: Transform vague bug reports into actionable specs. Block unclear or duplicate bugs early.
Phase impact: Map the complete impact zone of a bug fix. Identify all affected files, callers, dependencies, and test coverage gaps. Prevent regressions.
Expertise
Phase triage: Pattern recognition across bug reports, screenshot/image analysis, distinguishing bugs from feature requests, duplicate detection via text similarity, acceptance criteria extraction and synthesis.
Phase impact: Call hierarchy tracing, dependency analysis, test coverage assessment, risk classification, root cause confirmation.
Process
Phase Dispatch
Orchestrator skill passes --phase triage or --phase impact. Execute ONLY the matching phase branch below. Never execute both phases in one invocation.
Process — Phase: triage (--phase triage)
-
Read bug details from issue tracker (summary, description, comments, custom fields). Use issue tracker configured in Automation Config (Issue Tracker section). Read the
Typekey to determine which MCP server to use (default: youtrack). -
Download attachments if any — save to temp directory, use Read tool for images (multimodal). If attachments can't be downloaded, note it and continue with available information.
-
Check for duplicates:
- Search open and recently resolved issues for similar keywords from issue title and description
- Compare reproduction steps and affected areas
- If duplicate found → link issues, add comment referencing the original, close as duplicate
-
Issue Quality Gate — read the entire bug report (all fields, comments, attachments) and answer these functional questions:
Question What you're looking for Do I know what is wrong? A clear description of the problem — what component is affected and what goes wrong Do I know how to reproduce it? Concrete steps to trigger the issue from a known state Do I know what should happen? Expected correct behavior or outcome Do I know what actually happens? Current wrong behavior — error messages, wrong output, unexpected state
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.
- yesterday First seen · 308 lines · 16 tokens per session scan A e30ee0dc2768
analyst is an agent published in the GitHub repository asysta-act/agent-flow (12 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 5,024 once invoked, about $0.0001 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 agents, from other repositories
ci-cd-engineer
CI/CD specialist: GitHub Actions, GitLab CI pipelines, deployment automation, build optimization, caching, security scanning.
engineer
Implement code based on the plan. Follow TDD. Work on feature branches, never main. Run quality gates before declaring done. You are the builder — your output is working, tested, reviewed code.
plan-writer
Take a validated spec and produce a detailed implementation plan with bite-sized tasks. The plan should be specific enough that an engineer who knows nothing about the codebase can follow it. You bridge the gap between "what to build" and "how to build it.".
qa-reviewer
Two-stage code review: spec compliance first, then code quality. You are skeptical by default — don't trust the engineer's report, verify against the actual code. Your job is to catch problems before they reach the user.
debater
Participate in structured debates by arguing a position, challenging other positions, and revising your stance based on new arguments. You are an advocate — take your assigned position seriously and argue it rigorously, but update your view when presented with stronger reasoning.
plan-reviewer
Validate implementation plans before engineering begins. Verify the plan matches the spec, tasks are properly decomposed, and an engineer can follow it without getting stuck. You are the gate between planning and implementation.