feedback

A feedback-recording command for reporting that an earlier `.forge/` document needs revision after a later development, review, security, scaling, or incident stage.

In plain words
What is it for?
Use it to create a feedback entry for one upstream artifact, assign its review status and recommended change, check chain impact with `/sync`, and later rerun the relevant planning skill.
Why use it?
It prevents downstream work from silently changing upstream decisions and preserves the requested correction across sessions.

Command

Part of the forge-skills plugin — 6 skills, 36 commands, 13 agents, 1 hook shipped together

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/aneja5/forge-skills/feedback
Clone the repo
git clone --depth 1 https://github.com/aneja5/forge-skills

Or install forge-skills, the plugin that ships this one along with the rest of its 6 skills, 36 commands, 13 agents, 1 hook.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 184 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 $0.00018 $0.00184
Opus 5 $0.00009 $0.00092
Sonnet 5 $0.00004 $0.00037
Haiku 4.5 $0.00002 $0.00018

Measured 2d ago against content hash d79aa7fb0c51, 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.

commands/feedback.md · 14 lines

What it actually says

Invoke the feedback skill.

Capture a finding from build/review/secure/scale/incident into .forge/feedback/-.md. The entry targets ONE upstream artifact, declares severity (FEEDBACK_PENDING or NEEDS_REVIEW), and recommends a specific change.

This is the only sanctioned reverse-cascade primitive — never edit upstream artifacts directly during a downstream stage. The entry survives session boundaries; the next time the upstream skill runs, it reads pending entries and addresses them.

Reads: the source-stage context + the target artifact's current state Produces: .forge/feedback/-.md Next: run /sync to see chain impact; eventually re-run the targeted upstream skill (/spec, /architect, /plan, etc.) to resolve

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 · 14 lines · 18 tokens per session scan A d79aa7fb0c51

Subscribe to this mod's changes

feedback is a command published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 184 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.