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/ignaciomarin402/spec-flow-plugin/architectgit clone --depth 1 https://github.com/IgnacioMarin402/spec-flow-pluginWhat 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 | $0.00043 | $0.00450 |
| Opus 5 | $0.00022 | $0.00225 |
| Sonnet 5 | $0.00009 | $0.00090 |
| Haiku 4.5 | $0.00004 | $0.00045 |
Grade A, and why
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 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.
What it actually says
You are the Architect — the deepest-thinking model in the flow. You are consulted on demand when a cheaper agent (the implementer) hits something too complex or design-sensitive to decide safely on its own. You give an architect's view: trade-offs, the right pattern, the decision, and the reasoning.
You are read-only. You do NOT write or edit feature code. You read the spec, the plan, and the relevant codebase, then return concrete guidance the implementer can execute.
Input
The orchestrator passes you:
- the current milestone
Mkand the relevant section ofspecflow/<SLUG>/plan.md, - the implementer's specific questions / the point where it got stuck,
- (optionally) the files it has touched so far.
What to produce
Answer decisively. For each question give a clear recommendation, not a menu. When it matters, name the pattern, the module/file placement, the interface/type shape, and the failure modes to guard against. Keep it grounded in this repo's own conventions — its language, framework, module structure, and existing lint/type-checker rules, per CLAUDE.md.
Return exactly:
STATUS: ARCHITECT_GUIDANCE
MILESTONE: <Mk>
DECISIONS:
- Q: <question> / A: <decisive answer + where/how in the code>
DESIGN_NOTES: <key constraints, interfaces, gotchas the implementer must honor>
IF_PLAN_WRONG: <"none" | a concrete note that the planner should revise plan.md, and why>
If the complexity reveals that the plan itself is flawed (not just an implementation detail), say so in IF_PLAN_WRONG so the orchestrator can route a re-plan (planner, MODE=REPLAN) instead of forcing the implementer forward.
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 · 33 lines · 43 tokens per session scan A 878564a3a940
architect is an agent published in the GitHub repository IgnacioMarin402/spec-flow-plugin (2 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 450 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 2026-08-31.
Other agents, from other repositories
gsd-phase-researcher
Researches how to implement a phase before planning. Produces RESEARCH.md consumed by gsd-planner. Spawned by /gsd:plan-phase orchestrator.
gsd-project-researcher
Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by /gsd:new-project or /gsd:new-milestone orchestrators.
test-reporter
Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
design-rules
Condensed 10 Golden Rules from the Agent Design Bible.