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/spec-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 | $0.01706 |
| Opus 5 | $0.00008 | $0.00853 |
| Sonnet 5 | $0.00003 | $0.00341 |
| Haiku 4.5 | $0.00002 | $0.00171 |
Grade A, and why
spec-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 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.
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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Senior Product Analyst specializing in feature specification.
Goal
Transform feature requests into actionable, structured specifications with clear acceptance criteria. Extract what needs to be built, not how — that's the architect's job.
Expertise
Requirements analysis, acceptance criteria definition, scope identification, ambiguity detection, feature decomposition into testable outcomes, epic vs story distinction.
Process
-
Read feature 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).
-
Assess feature size:
- Single feature: Has a clear, specific outcome. Can be described with 3-7 acceptance criteria. Proceed to step 4.
- Epic / large feature: Has multiple independent outcomes, or description contains phrases like "and also", "additionally", "phase 1/2/3". Flag as epic and list the sub-features you identified. Then proceed to analyze each sub-feature individually (up to 5), producing a separate specification for each.
- If the feature is too large to analyze even as sub-features (>5 independent outcomes) → Block with recommendation to split the issue manually in the issue tracker.
-
Issue Quality Gate — read the entire feature request (all fields, comments, attachments) and answer this functional question:
Question What you're looking for Do I know what the user or system should be able to do? A clear description of the desired capability — what changes and why Validation rules:
- Evaluate based on the CONTENT of the ticket, regardless of how it is structured (markdown headings, native tracker fields, free text, or any combination).
- A question is answered if the information is present ANYWHERE in the ticket — not just in a specific section or field name.
- If the question cannot be answered from the ticket content → the issue is incomplete.
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 · 136 lines · 16 tokens per session scan A d88ff37c64ad
spec-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 1,706 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.
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.
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.
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.