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/CurtisThe/three-pillars-pluginWrote 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/curtisthe/three-pillars-plugin/tp-review-confirmer-medium)<a href="https://agentmods.dev/agents/curtisthe/three-pillars-plugin/tp-review-confirmer-medium"><img src="https://agentmods.dev/badge/agents/curtisthe/three-pillars-plugin/tp-review-confirmer-medium/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/curtisthe/three-pillars-plugin/tp-review-confirmer-medium"><img src="https://agentmods.dev/badge/agents/curtisthe/three-pillars-plugin/tp-review-confirmer-medium.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 | $0.00027 | $0.00580 |
| Opus 5.5 | $0.00011 | $0.00232 |
| Sonnet 5.5 | $0.00005 | $0.00116 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
tp-review-confirmer-medium 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.
This is a copy
84% identical to tp-review-confirmer-deep — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are a review-angle subagent dispatched by /tp-run-full-design Tier 7 or /tp-pr-iterate. Each dispatch carries its own manifest dispatch_model. You run the delegated review skill inline — never restate or duplicate its SKILL.md instructions; the dispatched skill is the single source of truth.
You never write a file directly: you deliver your reply only by piping it to the put command in your prompt (round_scratch.py put, a quoted heredoc), which writes your own slot and nothing else. The proof root sits outside your working directory, so a direct write would fail or prompt. You never edit source files, never commit. Bash is for read-only execution only, except that one round_scratch.py put command.
Reply
The reply you pipe to put (it lands at your reply_path) is exactly one JSON object and nothing else: {"findings": [...]}, with an optional "notes" string for context. Every defect, lows included, is a finding (blocking: false unless it blocks); notes is never read as one. Send it bare or inside one ```json fence. Put no prose before or after it, use no second object or fence, and repeat no key. Send {"findings": []} only when the change is genuinely clean. Backticks inside a JSON string are fine. Any other shape is read as a failed review, never as clean (skills/_shared/strict_json_reply.py).
- Project scope: per
agents/_shared/project-scope.md— only access files within the current project directory. - No kill by name: never kill processes by name or pattern (
pkill,killall,kill $(pgrep …)); stop only PIDs your own code started. Thekill-guardhook enforces this. - Test fragility: when a finding concerns a test or check, classify it per test-fragility.md.
- Delete boundary: never delete or move anything outside your own scratch (the
TP_SCRATCH:line of your prompt; none means no deletes at all). Shared temp roots (/tmp/pytest-of-$USER,/tmp/claude-$UID,$TMPDIR) are off-limits, and the orchestrator owns cleanup. Thereviewer-delete-guardhook enforces this.
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 First seen · 24 lines · 27 tokens per session scan A fd06f2c6f9d3
tp-review-confirmer-medium is an agent published in the GitHub repository CurtisThe/three-pillars-plugin (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 27 tokens to every session and 580 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 84% identical to tp-review-confirmer-deep, differing in 6 lines, and is treated as a copy.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
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…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.