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 skills add AhmedHabiba/architor --skill state-managergit clone --depth 1 https://github.com/AhmedHabiba/architorWrote 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/skills/ahmedhabiba/architor/state-manager)<a href="https://agentmods.dev/skills/ahmedhabiba/architor/state-manager"><img src="https://agentmods.dev/badge/skills/ahmedhabiba/architor/state-manager/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/skills/ahmedhabiba/architor/state-manager"><img src="https://agentmods.dev/badge/skills/ahmedhabiba/architor/state-manager.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 | $0.00059 | $0.01657 |
| Opus 5 | $0.00030 | $0.00829 |
| Sonnet 5 | $0.00012 | $0.00331 |
| Haiku 4.5 | $0.00006 | $0.00166 |
Grade A, and why
state-manager 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 10d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
State Manager
State File: .arch/state.json
This file is the single source of truth for project progress. ALWAYS read it before responding to any architecture query. NEVER rely on conversation memory for phase state. ALWAYS update it after every state change.
Reading State
- Parse the JSON file
- Check
current_phaseto know where we are - Check phase-specific status fields for detail
- For Phase 2, check
sub_phaseand individual acceptance flags (pattern_accepted, components_overview_accepted, cross_cutting_accepted) - For Phase 3, check
componentsobject for per-component status - Check
reopens.countandreopens.maxfor reopen availability
Example – read state (pseudocode; use the Read tool, not code execution):
state = Read(".arch/state.json") → parse JSON
current_phase = state["current_phase"]
Valid Phase Transitions
not_started → evaluation (when /analyze-prd runs)
evaluation → methodology (when Phase 1 is accepted)
methodology → components (when Phase 2 is fully accepted: pattern + components + cross-cutting)
components → finalization (when ALL components accepted)
Backward transitions are ONLY allowed via /reopen (max 2 per project).
Phase 2 Sub-Phases
pattern → components_overview → cross_cutting
Each sub-phase is accepted independently via /accept. All three must be accepted for Phase 2 to be complete.
Component Status Values
pending → in_progress (when /design-component starts)
in_progress → awaiting_acceptance (when design is presented)
awaiting_acceptance → accepted (when user accepts)
awaiting_acceptance → in_progress (when user refines)
needs-review → in_progress (after a reopen cascades)
Updating State
When updating state.json:
- Read current state
- Validate the transition is legal
- Write the updated state
- Increment
decision_countif a decision was made
Example – validate and write state (pseudocode; use Read/Write tools, not code execution):
VALID_TRANSITIONS = {
"not_started" → ["evaluation"],
"evaluation" → ["methodology"],
"methodology" → ["components"],
"components" → ["finalization"],
}
state = Read(".arch/state.json") → parse JSON
current = state["current_phase"]
if new_phase not in VALID_TRANSITIONS[current]:
# Invalid transition: do NOT write state.
# Report the error to the user and stop.
raise error: "Invalid transition: '{current}' → '{new_phase}'"
state["current_phase"] = new_phase
state["decision_count"] += 1
Write(".arch/state.json", JSON.stringify(state, indent=2))
What ships with it
19 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/instructions.json 9.0 KB
- evals/scenario-0/capability.txt 43 B
- evals/scenario-0/criteria.json 1.6 KB
- evals/scenario-0/task.md 2.2 KB
- evals/scenario-1/capability.txt 37 B
- evals/scenario-1/criteria.json 1.3 KB
- evals/scenario-1/task.md 2.0 KB
- evals/scenario-2/capability.txt 38 B
- evals/scenario-2/criteria.json 1.2 KB
- evals/scenario-2/task.md 1.5 KB
- evals/scenario-3/capability.txt 33 B
- evals/scenario-3/criteria.json 1.5 KB
- evals/scenario-3/task.md 1.9 KB
- evals/scenario-4/capability.txt 31 B
- evals/scenario-4/criteria.json 1.9 KB
- evals/scenario-4/task.md 2.1 KB
- evals/summary_infeasible.json 58 B
- evals/summary.json 1.0 KB
- tile.json 386 B
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.
- 10d ago First seen · 169 lines · 59 tokens per session scan A c6b8553ffdaa
state-manager is a skill published in the GitHub repository AhmedHabiba/architor (6 stars, last pushed 6mo ago), licensed MIT. It adds 59 tokens to every session and 1,657 once invoked, about $0.0003 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 skills, from other repositories
traction-eos
Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…
promote-idea
Converts an album idea from IDEAS.md into an actual album project in one step. Use when the user says "promote [idea title]", "turn idea into album", or "start working on [idea]".
customer-onboarding-and-implementation
Takes a new customer from signature to working — setting a definition of live that both sides agreed before the contract was signed, planning and staffing the implementation, running data migration and integration realistically, training the people who will actually use it, and handing over to the ongoing…
estimating-and-contingency
Produces a cost or effort estimate someone can defend — decomposing the work, choosing between analogous, parametric and bottom-up methods, documenting the basis and its assumptions, expressing confidence as a range, and sizing contingency and management reserve separately. Use this to build an estimate, challenge one…
vendor-management
Selects, contracts, and manages suppliers and vendors — requirements, evaluation, negotiation support, onboarding, performance management, and exit. Use this to choose a vendor, run a selection process, structure a service agreement's operational terms, manage an underperforming supplier, plan an exit or migration, or…
recap-doc
Post-development recap document generator. Use when: AI/Codex has implemented a feature and the user needs a guided walkthrough of what changed and why, with blind-spot detection and anticipated questions. Not for: Q&A follow-up (use /recap-ask), technical share-out for teammates (use /tech-brief), or generic code…