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.
npx skills add CSOAI-ORG/councilof-ai --skill platform-measuregit clone --depth 1 https://github.com/CSOAI-ORG/councilof-aiWrote 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/skills/csoai-org/councilof-ai/platform-measure)<a href="https://agentmods.dev/skills/csoai-org/councilof-ai/platform-measure"><img src="https://agentmods.dev/badge/skills/csoai-org/councilof-ai/platform-measure/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/skills/csoai-org/councilof-ai/platform-measure"><img src="https://agentmods.dev/badge/skills/csoai-org/councilof-ai/platform-measure.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 | $0.00074 | $0.00824 |
| Opus 5.5 | $0.00030 | $0.00330 |
| Sonnet 5.5 | $0.00015 | $0.00165 |
| Haiku 4.5 | $0.00007 | $0.00082 |
Grade A, and why
platform-measure 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Platform measure
The estate produces measurement artifacts, not revenue. That is only a problem if the harness itself is stuck. This skill measures the harness — the launchd lanes, cron jobs, daemons and MCP bridges that are supposed to be doing the work — and says, with receipts, which ones are actually carrying.
This is a subject-family measurement: it answers "is the instrument honest and still running", not
"how good is the product". It is the harness-fidelity slot. It is published against CSOAI's own
interest, so it is worth running.
Canonical implementation
The census is a real program with a frozen, sha-pinned method. Do not reimplement it inline; run it.
python3 ~/clawd/_alignment/platform-measure/csoai_console.py # live state + ranked actions
python3 ~/clawd/_alignment/platform-measure/measure_platforms.py # the census itself
python3 ~/clawd/_alignment/platform-measure/csoai_console.py --json
The console publishes nothing and sends nothing. It writes a dated receipt under
~/clawd/_alignment/platform-measure/receipts/. That receipt is the evidence; the console output is
the summary.
Method, method sha, runbook: ~/clawd/_alignment/platform-measure/RUNBOOK.md and
~/clawd/_alignment/platform-measure/bank/method-v2.json.
Verdict vocabulary — use exactly these
| Verdict | Meaning |
|---|---|
CARRYING |
the lane produced new bytes inside the sample window |
LOOPING |
the lane produced new bytes and every one of them is an error |
IDLE |
the lane is registered and alive but produced nothing in the window |
UNREACHABLE |
the lane's target could not be reached |
UNCHECKABLE |
the lane could not be read with confidence |
UNCHECKABLE is never FAIL. IDLE is not broken. A lane that produced no bytes has no count — it
is null, never zero.
Storage: measure the volume, not the container
A RunPod network volume is a slice of a petabyte MooseFS cluster, so statvfs reports the cluster
and not the volume. The container overlay (/) is the only genuinely tight filesystem, and it is
20 GB. When a lane reports a disk floor, check which filesystem it read before concluding the estate
is out of space. The estate's provisioned network volumes are counted in the RunPod account, not on
the container.
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 · 71 lines · 74 tokens per session scan A 1e388aa1ce0a
platform-measure is a skill published in the GitHub repository CSOAI-ORG/councilof-ai (3 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 824 once invoked, about $0.0003 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.
Other skills, from other repositories
ssh-incident
A diagnosis order for "the server is down", "the site is slow", "something broke". Use when investigating a problem on a remote server through the ssh tools, before changing anything.
deployment-completeness-audit
Read-only audit of changes that were built but not wired, deployed or exercised. Trace the target project's actual release path, runtime, migrations and adapters; report evidence and missing access honestly.
agentcore-investigation
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.
opik-explain
Root-cause a specific Opik trace, or a pattern across traces, and return a grounded explanation. Uses the hosted Opik MCP when it is connected, and falls back to SDK scripting otherwise. Returns the root cause, the evidence spans as clickable Opik UI links, and one suggested next step. Use for "why did this trace…
debug-failed-job
Find out why a Keboola job failed and propose a fix. Use when the user says a Keboola job, extractor, transformation, writer or flow failed or errored, or asks why their pipeline is red.
triaging-incidents
Creating, triaging, updating, and analyzing ServiceNow incidents, including trend reports. Assess severity, check affected CIs, find related incidents, and recommend assignments. Use when the user mentions incidents, INC numbers, outages, service disruptions, ticket creation, triage, priority, severity, ITSM…