feedback

A command for recording whether a Cohort agent or command was helpful or unhelpful, along with a short factual note. Cohort is the project's system for organizing agents and commands, and it stores feedback per project.

In plain words
What is it for?
Use it inside a Cohort project to rate an agent or command and record what worked or what was missing.
Why use it?
It captures user experience while it is fresh, giving later improvement proposals concrete evidence. It also keeps feedback separate from personal data, secrets, and credentials.

Command

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 commands/askwigconsulting/cohort/feedback
Clone the repo
git clone --depth 1 https://github.com/askwigconsulting/cohort
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 258 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 $0.00019 $0.00258
Opus 5 $0.00010 $0.00129
Sonnet 5 $0.00004 $0.00052
Haiku 4.5 $0.00002 $0.00026

Measured 2d ago against content hash 201116fff8fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feedback 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/commands/feedback.md · 29 lines

What it actually says

Record a piece of feedback about the office — the raw signal cohort propose-improvement aggregates.

Work out from the user's words (or ask) whether the rating is up or down and which agent or command it is about, then run:

cohort feedback --rating <up|down> [--agent <name> | --command <name>] [--note "<short note>"]

Keep the note short and factual — one sentence on what worked or what was missing. Notes may later be summarized into improvement proposals; do not put secrets, credentials, or personal data in them. Run it from inside the repo (feedback is recorded per project in .cohort/feedback/); if the repo is not a Cohort project yet, suggest cohort init.

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 · 29 lines · 19 tokens per session scan A 201116fff8fd

Subscribe to this mod's changes

feedback is a command published in the GitHub repository askwigconsulting/cohort (2 stars, last pushed 25d ago), licensed MIT. It adds 19 tokens to every session and 258 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.