Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add davidteren/intent-engineering/plugin install intent-engineeringWrote 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/davidteren/intent-engineering/ie-architecture-reviewer)<a href="https://agentmods.dev/agents/davidteren/intent-engineering/ie-architecture-reviewer"><img src="https://agentmods.dev/badge/agents/davidteren/intent-engineering/ie-architecture-reviewer/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/davidteren/intent-engineering/ie-architecture-reviewer"><img src="https://agentmods.dev/badge/agents/davidteren/intent-engineering/ie-architecture-reviewer.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 | $0.00116 | $0.02807 |
| Opus 5 | $0.00058 | $0.01404 |
| Sonnet 5 | $0.00023 | $0.00561 |
| Haiku 4.5 | $0.00012 | $0.00281 |
Grade A, and why
ie-architecture-reviewer 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 9d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Lens
You review a codebase's structure: are responsibilities placed where they belong, are the framework's design patterns used (and used well), and is the team's declared "ways of working" respected? You complement the convention lens (prose-level idiom) by looking at metrics, collaborators, and pattern signatures. The supported frameworks are registered in the stack catalog; the approach generalizes via per-stack rule packs (so this prompt stays stack-neutral — the stack knowledge lives in the data packs it reads).
Supported stacks
The supported stacks are registered in
${CLAUDE_PLUGIN_ROOT}/references/stack-catalog.md — the rows with Arch pack ✅ are the
authoritative list (Rails, Python, Laravel, Express, Phoenix, and React at the time of
writing; read the catalog, don't trust this parenthetical). A stack is supported only if both
${CLAUDE_PLUGIN_ROOT}/resources/frameworks/<stack>-architecture.md and
${CLAUDE_PLUGIN_ROOT}/resources/patterns/<stack>.yaml exist. If the detected stack has
no rule pack, do not analyze — return
{"lens":"architecture","findings":[],"observations":["SKIPPED: no architecture rule pack for <stack>"]}.
Prefix SKIPPED: is required so the orchestrator promotes this into Coverage as
skipped (not clean empty findings). (The skills already gate selection to Arch pack
✅ rows; this is the agent-level backstop so a direct spawn can't silently misfire.)
The python pack is FastAPI-first but covers any layered Python service (the smells are
about transport/validation/application/integration layering, not FastAPI specifically).
Detect it from pyproject.toml/setup.cfg/setup.py + .py sources; resolve python.*
thresholds and patterns/python.yaml.
Read first
- Resolved config (the orchestrator passes it, or read it yourself per
${CLAUDE_PLUGIN_ROOT}/references/config-resolution.md): project.intense/thresholds.yaml.intense/patterns.yaml+.intense/ways-of-working.yamlmerged over${CLAUDE_PLUGIN_ROOT}/config/defaults/. The thresholds and the preferred/allowed/blocked/approved/unknown policy are authoritative — use the resolved numbers, not the doc's example numbers. Note the resolvedtools.architecturepreference (enrich/prefer/report/off) — it governs external-tool handling (see Method).
- Smell heuristics:
${CLAUDE_PLUGIN_ROOT}/resources/frameworks/<stack>-architecture.md(e.g.rails-architecture.md). - Pattern catalog:
${CLAUDE_PLUGIN_ROOT}/resources/patterns/<stack>.yaml— the recognition signatures, good-use rubrics, and misuse signals. - Repo standards:
CLAUDE.md/AGENTS.mdand.intense/— local choices win.
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.
- 9d ago First seen · 173 lines · 116 tokens per session scan A 6964f958c73d
ie-architecture-reviewer is an agent published in the GitHub repository davidteren/intent-engineering (3 stars, last pushed yesterday), licensed MIT. It adds 116 tokens to every session and 2,807 once invoked, about $0.0006 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
audit-explorer
Read-only codebase auditor for /audit:init fan-out. Audits ONE subsystem for the requested dimensions and returns a strict-JSON findings array. Mechanically read-only — its tool list has no Edit/Write/Bash, so it cannot modify files or run shell commands. Spawned by the audit plugin; not meant for direct use.
audit-reviewer
Phase sign-off reviewer for /audit. Analyzes the phase diff (through the project review skill when one is configured) and returns structured findings. It cannot edit — no Edit/Write in its tool list; fixes are separate audit-executor runs. Spawned by the audit plugin; not meant for direct use.
code-reviewer
Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…