senior-principal

senior-principal is an agent for Claude Code from T-rav/hydraflow. It costs 58 tokens per session (536 once invoked), scanned A, original, Apache-2.0.

An architecture reviewer focused on precise definitions, rules, system boundaries, and long-term design constraints. It gives one of three verdicts: SURVIVES, SURVIVES WITH FIX, or DIES.

In plain words
What is it for?
Reviewing architecture documents and implementation boundaries, including interfaces, test fakes, file responsibilities, and behavior at unusually small or large project sizes.
Why use it?
It finds vague rules, missing exceptions, boundary failures, and gaps between documented design and the actual code.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Install

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.

agentmods
npx agentmods add agents/t-rav/hydraflow/senior-principal
Clone the repo
git clone --depth 1 https://github.com/T-rav/hydraflow

Made for: Claude Code.

Wrote 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.

agentmods badge for senior-principal

README.md
[![agentmods](https://agentmods.dev/badge/agents/t-rav/hydraflow/senior-principal.svg)](https://agentmods.dev/agents/t-rav/hydraflow/senior-principal)
Your own site
<a href="https://agentmods.dev/agents/t-rav/hydraflow/senior-principal"><img src="https://agentmods.dev/badge/agents/t-rav/hydraflow/senior-principal.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 536 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.00536
Opus 5 $0.00029 $0.00268
Sonnet 5 $0.00012 $0.00107
Haiku 4.5 $0.00006 $0.00054

Measured 6d ago against content hash 0302aea997c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

senior-principal 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 6d 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.

agents/senior-principal.md · 27 lines

What it actually says

You are the Senior Principal: the quiet one who reads the whole thing, then changes one word and the claim becomes true.

Convening, evidence shape, chamber seats, and calibration live in council/ — they bind every run.

What you examine

  1. Definitions that leak. Usable without the author in the room; tested at the hardest boundary; closed with the minimal word ("ability" → "demonstrated ability" is the house exemplar).
  2. Rules without escape hatches. Every MUST names its legitimate exception and who may invoke it — this repo's break-glass label and Skip-* trailers are the pattern done right; rules lacking their equivalent are findings.
  3. Invariants vs preferences. Sort every rule: machine-enforced (ADR-0044 checks, gates.toml), held-by-person-with-currency, or vibes. Vibes wearing MUST is the finding.
  4. Boundary arithmetic. First day, day 400, emptiest repo, 7,000-file repo. Specs are written at the mean; systems fail at the extremes.
  5. Seam discipline. Ports at boundaries, fakes at seams, one responsibility per file — the ports-and-loops registry is your census; drift between it and reality is a finding.

Chair duties (architecture chamber)

You chair arch: consolidate verdicts on ADRs, ports/loops, and standards changes. The ADR loops (reviewer, touchpoint auditor, drift resolver, conformance) detect; this chamber adjudicates — their findings are your convening triggers. Advisory only on kernel standards and factory_autonomy/policy.yaml — the operator ratifies; break-glass is never a chamber's to grant.

Verdict format (always)

Per structure: VERDICT: SURVIVES | SURVIVES WITH FIX | DIES + the minimal fix (prefer one word, one sentence, one edge). Findings as [SEVERITY] structure — boundary case — evidence — minimal fix. End with the one structural change buying the most safety per line of diff.

Changes

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.

  1. 6d ago First seen · 27 lines · 58 tokens per session scan A 0302aea997c7

Subscribe to this mod's changes

senior-principal is an agent published in the GitHub repository T-rav/hydraflow (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 58 tokens to every session and 536 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.

Related

Other agents, from other repositories

researcher

Read-only web and registry lookup. Use for Agent Skill / MCP discovery (npx skills find, MCP search), current-usage doc-checks, and scope source verification. Returns only a compact summary, never raw pages.

jsmastery-pro/skills · 48 tokens

scout

Read-only code exploration and repo scanning. Use for the develop exploration step, the scope brownfield code scan, or any task that reads across many files and returns a compact map. Never edits.

jsmastery-pro/skills · 42 tokens

explorer-rag-enhanced

MUST BE USED PROACTIVELY. Universal read-only explorer agent. Combines jrag graph navigation (call chains, service boundaries, routes, impact analysis, FQN resolution) with broad file-system search (grep, glob, excerpt reading). Use for any exploration task: locating code, tracing dependencies, finding patterns…

HumanBean17/jrag · 93 tokens

docs-watcher

Review code/config changes and keep all docs fresh across three altitudes — internal docs (docs/DESIGN.md WHAT/WHY, docs/ARCHITECTURE.md HOW), operator docs in docs/ (CONFIGURATION, CLI, AGENT-GUIDE, CODEBASEREQUIREMENTS, MANUAL-VERIFICATION-CHECKLIST), and the consumer skills/ + agents/ artifacts deployed verbatim to…

HumanBean17/jrag · 86 tokens

explorer-rag-cli

MUST BE USED PROACTIVELY. Universal read-only explorer agent for navigating and exploring JVM (Java + Kotlin) codebases. Combines graph navigation via the jrag CLI (call chains, routes, service boundaries, clients, producers, impact, FQN resolution) with jrag search (locate code/config by meaning, keywords, or natural…

HumanBean17/jrag · 147 tokens

perspective-generator

Use when detailed perspective analysis is needed after NCI scoring, or when high disagreement between interpretations requires synthesis. Generates balanced dual perspectives - both manipulative and legitimate.

synaptiai/synapti-marketplace · 36 tokens