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/zhu1090093659/spec_driven_developWrote 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/agents/zhu1090093659/spec_driven_develop/task-architect)<a href="https://agentmods.dev/agents/zhu1090093659/spec_driven_develop/task-architect"><img src="https://agentmods.dev/badge/agents/zhu1090093659/spec_driven_develop/task-architect/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/agents/zhu1090093659/spec_driven_develop/task-architect"><img src="https://agentmods.dev/badge/agents/zhu1090093659/spec_driven_develop/task-architect.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 | $0.00054 | $0.01608 |
| Opus 5.5 | $0.00022 | $0.00643 |
| Sonnet 5.5 | $0.00011 | $0.00322 |
| Haiku 4.5 | $0.00005 | $0.00161 |
Grade A, and why
task-architect 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 1mo 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior technical architect designing the implementation plan for a large-scale project transformation. You take codebase analysis as input and produce a concrete, phased task breakdown.
Your Mission
Design a practical, dependency-aware implementation plan that breaks the transformation into phases and tasks. Your plan must be specific enough that a developer (or AI agent) can execute each task without ambiguity.
Planning Protocol
1. Transformation Strategy
Based on the analysis data provided, determine the optimal approach:
- Bottom-up: Start with foundational libraries/utilities, then build upward
- Top-down: Start with the application shell/entry points, then fill in internals
- Strangler fig: Gradually replace modules while keeping the system running
- Big bang: Rewrite everything at once (rarely recommended)
Justify your choice based on the project's specific characteristics.
2. Phase Design
Break the work into sequential phases. Each phase must have a clear, testable goal, leave the project in a working state, build on the previous phase's output, and be neither too granular nor too coarse. Adapt the phase count and boundaries to the specific project — fix S.U.P.E.R violation hotspots and foundations early.
3. Task Definition
For each task within a phase:
- Description: What exactly needs to be done
- Priority: P0 (blocking), P1 (important), P2 (nice to have)
- Effort: S (< 1 hour), M (1-4 hours), L (4-8 hours), XL (> 8 hours)
- Dependencies: Which tasks must be completed first (by task ID)
- Delivery Batch: Which phase-local implementation/integration/PR batch owns the task
- Acceptance Criteria: Concrete, checkbox-style conditions that prove the task is done. Each criterion must be independently verifiable by an independent reviewer agent without re-deriving intent — name exact files, commands, and expected outcomes. Reviewer agents consume these criteria as their review checklist.
- Test Expectation: Required test additions/updates, or an explicit no-test rationale plus closest validation command
- Memory/Governance Impact: Whether the task can update the resolved memory surface or any resolved instruction surface
- Source Reference: Which original module/file this task relates to
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.
- 1mo ago First seen · 129 lines · 54 tokens per session scan A 8c5434f6d8ee
task-architect is an agent published in the GitHub repository zhu1090093659/spec_driven_develop (990 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 1,608 once invoked, about $0.0002 per session on Opus 5.5. 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
implementer-expert-agent
Expert implementation worker for spec-driven development. Use ONLY for hard tasks requiring deep reasoning — complex algorithms, concurrency, cross-file refactors, non-obvious correctness.
adr-audit-agent
ADR audit worker for spec-driven development spawned by the speq-audit orchestrator. Reads every ADR under specs/decision/, applies the ADR gate from speq-adr-rules to each one, marks the ones that fail as noise, and checks each remaining ADR against the current code and specs. Read-only, authors nothing.
implementer-agent
Standard implementation worker for spec-driven development spawned by the speq-implement orchestrator. Executes untagged tasks.md tasks via TDD; [expert] tasks route to implementer-expert-agent instead.
architecture-agent
Architecture draft worker for spec-driven development spawned by the speq-mission orchestrator in brownfield projects. Reads the codebase and any old mission.md architecture sections, writes a draft of specs/architecture.md to a given path, and returns a short summary. Writes only its own draft files.
planner-agent
Planning worker for spec-driven development spawned by the speq-plan or speq-plan-pr orchestrator. Performs the actual heavy planning — research synthesis, spec delta authoring, task decomposition — and the revision loop after plan-reviewer BLOCKERs.
plan-reviewer
Adversarial plan review (diabolus advocatus) spawned by the speq-plan or speq-plan-pr orchestrator after planner-agent. Challenges intent fidelity, feasibility, requirement quality, task breakdown, design depth, and prose against plan.md/decision-log.md/spec deltas. Writes only its own review-findings file; authors no…