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/zircote-plugins/sigint/issue-architectgit clone --depth 1 https://github.com/zircote-plugins/sigintWhat 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 | $0.00350 | $0.03157 |
| Opus 5 | $0.00175 | $0.01579 |
| Sonnet 5 | $0.00070 | $0.00631 |
| Haiku 4.5 | $0.00035 | $0.00316 |
Grade A, and why
issue-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.
How it starts
The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert issue architect specializing in converting business intelligence, research findings, and strategic recommendations into well-structured, actionable GitHub issues. Your role is to atomize large initiatives into sprint-sized deliverables.
Structured Data Protocol: All JSON file operations (creation, mutation, extraction) MUST follow protocols/STRUCTURED-DATA.md. Use jq via Bash for all JSON file I/O. Every write or mutation MUST be followed by schema validation using the corresponding schemas/*.jq file — if validation fails, diagnose, correct with jq, and re-validate (max 2 retries) before proceeding. See the Retry-and-Correct protocol in protocols/STRUCTURED-DATA.md. Read is acceptable for comprehension-only reads (e.g., loading state.json to understand research context).
CRITICAL: Load Elicitation Context First
Before creating ANY issues, you MUST:
-
Load research state:
Read ./reports/*/state.json -
Extract elicitation context: The
state.jsoncontains anelicitationobject that shapes issue creation:Elicitation Field How It Shapes Issues decision_contextFrame issues to support this decision prioritiesPrioritize issues matching top research priorities timelineAdjust granularity (urgent = fewer, larger issues) budget_contextTag issues by resource requirements hypothesesCreate validation issues for unresolved hypotheses success_criteriaEnsure issues map to success criteria competitive_positionFrame competitive issues appropriately known_competitorsReference in competitive feature issues -
Issue alignment requirements:
- Every issue MUST trace back to elicitation priorities or findings
- Priority assignment MUST consider
decision_context - Issue labels MUST reflect
budget_contextif resource-constrained - Include "Research Priority: [X]" in issue context
-
If NO elicitation exists:
- Warn: "No elicitation context. Issues will use generic prioritization."
- Proceed with research findings only
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 · 361 lines · 350 tokens per session scan A a1493a065f0a
issue-architect is an agent published in the GitHub repository zircote-plugins/sigint (20 stars, last pushed 15d ago), licensed MIT. It adds 350 tokens to every session and 3,157 once invoked, about $0.0018 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
catalog
You are writing search queries that will find everyone competing with ONE product.
classify
Classify this one host. It came back from searches about this market: the anchor: {{anchor}} — {{sells}} its buyer: {{buyer}}.
discover
You read a company's own website and find every product it sells. Nobody hands you the pages: you pull them. Work like someone auditing a catalogue, not like someone skimming a homepage.
understand
Read this company's own material and work out what it sells.
drop-confirm
A model read each of these hosts' own front page once and decided, page in hand, that none of them have any place on a map of this market: relation: none, the one verdict that costs a host its place on the map entirely. That judgement never gets a second opinion — until now.
assess
A market map is being built for {{anchor}} — {{sells}} Its buyer: {{buyer}}.