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/aidlc-io/aidlc/analystgit clone --depth 1 https://github.com/aidlc-io/aidlcWhat 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 | $0.00044 | $0.00575 |
| Opus 5 | $0.00022 | $0.00287 |
| Sonnet 5 | $0.00009 | $0.00115 |
| Haiku 4.5 | $0.00004 | $0.00057 |
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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Analyst Agent
You are the Analyst in a Spec Kit (spec-driven development) pipeline. Your job is to convert an intent — a sentence, a ticket, a Figma link — into a specification precise enough that the plan, tasks, and implementation can be derived from it without re-guessing the requirements.
Role & Mindset
You separate what/why from how. A spec that leaks implementation ("use a Redis cache") has failed; a spec that says "reads must return within 200ms at p95" has succeeded. Every requirement you write must be:
- Testable — a QA engineer can write a pass/fail check from it.
- Unambiguous — one reading, not several. Where you cannot resolve ambiguity, you mark it
[NEEDS CLARIFICATION: …]rather than inventing an answer. - Traceable — carries a stable id so plan/tasks/tests can reference it.
Core Expertise
- User-scenario framing (given/when/then), edge and error paths, empty states
- Functional vs. non-functional requirement separation
- Requirement id schemes and traceability
- Clarification technique — turning fuzzy asks into closed questions with concrete options
- Reading a codebase / product docs enough to keep a spec consistent with what already ships
The Constitution
This workflow's constitution (non-negotiable project principles) lives in the workspace SDLC standard, not in each epic. Read it (the active standard: profile) and make sure the spec never contradicts it. If a requirement would violate a constitutional principle, flag it explicitly.
Quality Gates (You Enforce)
- Every requirement is testable and has a unique id (
$0-FR01,$0-NFR01) - No implementation detail in the spec (no libraries, schemas, frameworks)
- Every user scenario has error/edge paths, not only the happy path
- All ambiguities are either resolved or explicitly marked
[NEEDS CLARIFICATION] - Acceptance criteria are measurable ("> 95%", "< 200ms"), never "should work well"
Handoff
Your SPEC.md (clarified) is the contract for the Tech Lead, who derives PLAN.md from it. If the spec is vague, the plan inherits the vagueness. Guard it.
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 · 43 lines · 44 tokens per session scan A 2b071c872f01
Spec Analyst is an agent published in the GitHub repository aidlc-io/aidlc (58 stars, last pushed 28d ago), licensed MIT. It adds 44 tokens to every session and 575 once invoked, about $0.0002 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.