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 agentmods add commands/aneja5/forge-skills/feedbackgit clone --depth 1 https://github.com/aneja5/forge-skillsWhat 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 | $0.00018 | $0.00184 |
| Opus 5 | $0.00009 | $0.00092 |
| Sonnet 5 | $0.00004 | $0.00037 |
| Haiku 4.5 | $0.00002 | $0.00018 |
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.
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
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.
- 2d ago First seen · 14 lines · 18 tokens per session scan A d79aa7fb0c51
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.
Other commands, from other repositories
index
Command "index" from cesarandreslopez/tauri-agent-tools, covering command reference, command summary, categories, visual capture and dom inspection.
console-monitor
Monitor console output (log/warn/error/info/debug) in real-time.
eval
Evaluate a JavaScript expression in the Tauri app's webview.
info
Show window geometry and display server info.
list-windows
List all visible windows, marking Tauri apps.
git
Unified git operations - commits, pull requests, and issue management.