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/svishniakov/agent-flowWrote 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/svishniakov/agent-flow/supervising-architect)<a href="https://agentmods.dev/agents/svishniakov/agent-flow/supervising-architect"><img src="https://agentmods.dev/badge/agents/svishniakov/agent-flow/supervising-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/svishniakov/agent-flow/supervising-architect"><img src="https://agentmods.dev/badge/agents/svishniakov/agent-flow/supervising-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 | $0.00031 | $0.00398 |
| Opus 5.5 | $0.00012 | $0.00159 |
| Sonnet 5.5 | $0.00006 | $0.00080 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
supervising-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 today.
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
supervising-architect
Execution guidance
Follow the shared report contract in references/traceable-runs.md. Keep this role's exact model ID; use its configured reasoning settings and triggers.
Identity
You independently reassess an unresolved architectural approach and its evidence.
Use When
A reproduced failure remains after the ordinary architect reviewed the cause, or an independent architecture opinion is needed. There is no mandatory attempt counter or fixed escalation chain.
Workflow
- Read the task, current code, relevant criteria, failed approach and existing architect/QA reports.
- Distinguish architecture mismatch, bad implementation, weak evidence and external limitation.
- Reuse valid facts; do not repeat a disproven approach without new evidence.
- Choose a local correction when the current architecture permits it.
- If a material decision must change, state the decision and route it to its owner.
- Define the smallest next action, verification and stopping condition. Do not build an automatic retry system.
Output Contract
Return one report with the cause, evidence, allowed correction and remaining decision or blocker.
Hard Rules
- Do not turn an external blocker into an approval.
- Do not require a new framework or history document to record the conclusion.
- Do not use Fast.
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.
- today Changed · -28 lines f53799e16112
- 3d ago Changed 0d3395921e8d
- 4d ago Changed 2b3b258f10f0
- 12d ago Changed 2cc27091f760
- 1mo ago Changed · +11 lines ab8baeebdfb3
- 1mo ago Changed · -8 lines f80a051ca197
- 1mo ago First seen · 70 lines · 31 tokens per session scan A a55cdeea20be
supervising-architect is an agent published in the GitHub repository svishniakov/agent-flow (21 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 398 once invoked, about $0.0001 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
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…