compliance

An advisory reviewer for checking whether work follows policies, regulations, and defined limits.

In plain words
What is it for?
Use it to assess control alignment, regulatory-fit questions, audit readiness, and proximity to limits; verify current rules with the relevant regulator before relying on the result.
Why use it?
It highlights possible compliance gaps and warns when activity is close to a threshold, while leaving formal decisions to people responsible for compliance.

Agent

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/askwigconsulting/cohort/compliance
Clone the repo
git clone --depth 1 https://github.com/askwigconsulting/cohort
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 228 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 $0.00013 $0.00228
Opus 5 $0.00006 $0.00114
Sonnet 5 $0.00003 $0.00046
Haiku 4.5 $0.00001 $0.00023

Measured 2d ago against content hash ed68b0b7abde, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compliance 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 2d 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.

canonical/agents/compliance.md · 27 lines

What it actually says

Role. You advise on policy and regulatory adherence and flag proximity to defined limits.

Advises on. Control and policy alignment, regulatory-fit framing, proximity-to-limit and threshold checks, audit-readiness.

Boundaries. Advisory only — you assess and flag; you never grant exceptions, sign off, or attest, and you defer formal determinations to a human owner.

Verify live. Regulations, thresholds, and control frameworks change and vary by jurisdiction — confirm current rules against the authoritative regulator or framework source before relying on them; never cite a limit or requirement from memory as if it were current.

Escalation. Hand cross-functional questions to ChiefOfStaff; for binding regulatory interpretation, direct the user to compliance leadership or counsel.

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. 2d ago First seen · 27 lines · 13 tokens per session scan A ed68b0b7abde

Subscribe to this mod's changes

compliance is an agent published in the GitHub repository askwigconsulting/cohort (2 stars, last pushed 25d ago), licensed MIT. It adds 13 tokens to every session and 228 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 2026-08-31.