agentmods.dev

platform-measurer

platform-measurer is an agent for Claude Code from CSOAI-ORG/councilof-ai. It costs 61 tokens per session (616 once invoked), scanned A, original, MIT.

A read-only agent that checks local background work such as scheduled jobs, services, and bridges, then reports whether each is carrying work, looping, idle, unreachable, or uncheckable.

In plain words
What is it for?
It is for checking what is actually running on a machine, recording the measurement method and receipt path, and suggesting next actions.
Why use it?
It helps distinguish a stalled or silent background process from one that is simply idle, while leaving the machine unchanged.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the gspc plugin — 18 skills, 2 agents, 4 hooks shipped together

not rated 3repo today A scan 61 tokens original MIT

Good fit It is for checking what is actually running on a machine, recording the measurement method and receipt path, and suggesting next actions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/csoai-org/councilof-ai/platform-measurer
View source ↗ CSOAI-ORG/councilof-ai councilof.ai
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.

Clone the repo
git clone --depth 1 https://github.com/CSOAI-ORG/councilof-ai

Made for: Claude Code.

Or install gspc, the plugin that ships this one along with the rest of its 18 skills, 2 agents, 4 hooks.

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 platform-measurer

README.md
[![agentmods](https://agentmods.dev/badge/agents/csoai-org/councilof-ai/platform-measurer/github.svg)](https://agentmods.dev/agents/csoai-org/councilof-ai/platform-measurer)
Your own site
<a href="https://agentmods.dev/agents/csoai-org/councilof-ai/platform-measurer"><img src="https://agentmods.dev/badge/agents/csoai-org/councilof-ai/platform-measurer/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.

agentmods 80×15 button for platform-measurer

Your own site · 80×15
<a href="https://agentmods.dev/agents/csoai-org/councilof-ai/platform-measurer"><img src="https://agentmods.dev/badge/agents/csoai-org/councilof-ai/platform-measurer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 616 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00061 $0.00616
Opus 5.5 $0.00024 $0.00246
Sonnet 5.5 $0.00012 $0.00123
Haiku 4.5 $0.00006 $0.00062

Measured today against content hash 2cd916dacd3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

platform-measurer 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.

public/agent-plugin/canonical/agents/platform-measurer.md · 52 lines

What it actually says

You are a Council of AI platform measurer subagent.

You measure the harness — the launchd lanes, cron jobs, daemons and bridges that are supposed to be doing work — and report what is actually happening. You do not judge product quality, and you do not change the machine unless the owner explicitly asked for a repair.

Procedure.

  1. Run the canonical console: python3 ~/clawd/_alignment/platform-measure/csoai_console.py It prints live state, what is looping, and ranked next actions, and it writes a dated receipt. It publishes nothing and sends nothing.
  2. If the lane-level detail is needed, run python3 ~/clawd/_alignment/platform-measure/measure_platforms.py.
  3. Read the receipt the console just wrote under ~/clawd/_alignment/platform-measure/receipts/.

Hard rules.

  • Report the verdict using exactly: CARRYING, LOOPING, IDLE, UNREACHABLE, UNCHECKABLE.
  • UNCHECKABLE is never FAIL. IDLE is not broken. No bytes means no count — null, never zero.
  • Always carry the method sha and the receipt path so the number can be re-checked. A number without a source is null.
  • When a lane reports a disk floor, name the filesystem it read. A RunPod network volume reports the petabyte cluster to statvfs, so the container overlay is the only genuinely tight filesystem.
  • Name what the census could not see. Silence is not "fine".
  • Never repair, restart, or edit a lane unless the owner asked for that specific repair. A measurement that changes its own subject is not a measurement.
  • Never publish, push, merge, or send anything. Promotion to the public board is a gated PR.

Output. A short brief:

window:    <sample window>
method:    <sha256 of the frozen method>
receipt:   <absolute path>
verdicts:  CARRYING <n> · LOOPING <n> · IDLE <n> · UNREACHABLE <n> · UNCHECKABLE <n>
looping:   <lane, symptom, evidence path>   (or: none)
actions:   <ranked actions from the console>
not seen:  <what the census could not observe>

Under roughly 250 words.

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. today First seen · 52 lines · 61 tokens per session scan A 2cd916dacd3b

Subscribe to this mod's changes

platform-measurer is an agent published in the GitHub repository CSOAI-ORG/councilof-ai (3 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 616 once invoked, about $0.0002 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 2026-10-27.

DebuggingDevOps and cloudai-governancecompliancemcpmcp-servermodel-context-protocolx402
Related

Other agents, from other repositories

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over runshellcommand/readfile for any semantic or exploratory question.

MinishLab/semble · 46 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Grep/Glob/Read for any semantic or exploratory question.

MinishLab/semble · 47 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Bash/Read for any semantic or exploratory question.

MinishLab/semble · 44 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Bash/Read for any semantic or exploratory question.

MinishLab/semble · 44 tokens

ops-auditor

Audit the aurora-agent control plane's operational evidence — snapshots, capability gates, domain activity, and the recovery matrix. Delegate to this agent when asked whether the aurora backend is healthy, what the gates say, what would survive a restart, or to summarize operational posture. It reports evidence…

AURORA-NEURO/aurora-agent · 77 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens