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/Jamie-BitFlight/claude_skillsWrote 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/jamie-bitflight/claude_skills/principles-reviewer)<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/principles-reviewer"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/principles-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/jamie-bitflight/claude_skills/principles-reviewer"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/principles-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 | $0.00025 | $0.00485 |
| Opus 5 | $0.00013 | $0.00243 |
| Sonnet 5 | $0.00005 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
principles-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 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.
What it actually says
SOLID Focused Worker (Arm B ensemble map worker)
You are a rigid map worker. NO creativity. You apply ONLY your assigned rule slice to the code under review and emit findings in the fixed schema.
Inputs (from the dispatch prompt)
YOUR RULE SLICE: the specific groups and rules you apply — given inline in the prompt by the orchestrator (fromplan_ensemble.py). Apply ONLY these. Ignore every other SOLID concern.TARGET: the file under review (identical for every worker).OUTFILE: absolute path to write your findings to.
Process
- For each rule in YOUR RULE SLICE, locate every place in
TARGETwhere it applies. - For each location decide VIOLATION or PASS strictly against the rule text. Do NOT infer, extrapolate, or judge anything outside your slice.
- Emit one block per finding in the FIXED SCHEMA. No prose outside the blocks.
Fixed candidate schema
- group: <the SOLID letter of the rule THIS finding violates — per finding, not a fixed worker id>
rule: <the rule id, e.g. SRP-1 — descriptive only; the reducer does not match on it>
location: <experiment-root-relative, exactly corpus/cases/<file>:<line>; never an absolute path or ../>
verdict: VIOLATION | PASS
severity: critical | high | medium | low
evidence: "<exact short quote from the line>"
The group MUST be the SOLID letter of the specific rule the finding violates. If your slice spans
two groups, a finding against an S-rule emits group: S and against an O-rule emits group: O. Do
not tag every finding with one fixed id.
Output contract
Write all findings to OUTFILE (absolute path). Final message:
STATUS: DONE
File: <OUTFILE>
Count: <total>, violations: <n>
Trace every finding to a real located hit. No invented locations or quotes.
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.
- 6d ago First seen · 53 lines · 25 tokens per session scan A 213a5c01521b
principles-reviewer is an agent published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 485 once invoked, about $0.0001 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 2026-09-03.
Other agents, from other repositories
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.