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 aneja5/forge-skills --skill feedbackgit clone --depth 1 https://github.com/aneja5/forge-skillsWrote 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/aneja5/forge-skills/feedback)<a href="https://agentmods.dev/skills/aneja5/forge-skills/feedback"><img src="https://agentmods.dev/badge/skills/aneja5/forge-skills/feedback/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/aneja5/forge-skills/feedback"><img src="https://agentmods.dev/badge/skills/aneja5/forge-skills/feedback.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 | $0.00065 | $0.01885 |
| Opus 5.5 | $0.00026 | $0.00754 |
| Sonnet 5.5 | $0.00013 | $0.00377 |
| Haiku 4.5 | $0.00006 | $0.00188 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feedback (reverse cascade)
Overview
Capture a finding from any downstream stage into a structured .forge/feedback/<timestamp>-<source>.md entry that targets one upstream artifact. The entry stays as status: PENDING until the upstream skill re-runs and addresses it. forge-sync flags the target artifact as FEEDBACK_PENDING until the entry is resolved.
This is the only sanctioned reverse-cascade primitive. The forward chain (prd → arch → tasks → code) flows one direction; backward propagation happens through these entries, not by directly editing upstream artifacts mid-stream.
When to Use
- During
/buildyou discover the relevant contract is missing an operation or has the wrong shape - During
/reviewyou find an architectural flaw that wasn't visible at design time - During
/secureor/scaleyou produce a recommendation that implies architecture changes (add a WAF, change a data store, add a gateway) - During an incident you discover an error path the error-handling spec didn't cover
- After a sprint, you realize ≥3 tasks split mid-flight — the plan needs an update before the next sprint
When NOT to Use
- The fix is fully contained inside the current stage (don't escalate every implementation detail)
- You have permission to edit the upstream artifact directly and want to do so — then just edit it;
forge-syncwill flag downstream as STALE - The finding is a question, not a recommended change — discuss with the user first; file the entry once a recommendation crystallizes
- The target artifact doesn't exist (
.forge/security.mdnot yet generated) — run the source skill instead
Common Rationalizations
| Thought | Reality |
|---|---|
| "I'll just edit the contract inline" | Then the chain has no record of WHY it changed. Future readers see a contract that contradicts the PRD with no explanation. |
| "Filing a feedback entry is overhead — I'll fix it later" | "Later" means the finding is forgotten by the time the upstream skill re-runs. The entry is the memory. |
| "The upstream skill will figure it out when it re-runs" | The upstream skill regenerates from its inputs, not from the downstream's discovery. Without a feedback entry, the regenerated artifact has the same flaw. |
| "This is too small for a feedback entry" | Three small findings ignored = one big surprise at /ship. |
| "I'll just tell the user verbally" | Verbal findings evaporate. The entry survives session boundaries. |
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.
- 1mo ago First seen · 143 lines · 65 tokens per session scan A 436dfd870297
feedback is a skill published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 5mo ago), licensed MIT. It adds 65 tokens to every session and 1,885 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 2026-09-03.
Other skills, from other repositories
link-ticket-to-session
Link the current Claude Code session to a ticket (Linear, Jira, GitHub Issues, or GitHub Pull Requests) and cache its title/status in karma. Use when the user explicitly asks to link, attach, associate, or connect this session to a ticket, issue, or PR — e.g. "/link-ticket-to-session ABC-123", "link this session to…
lead
Use when acting as the factory tech lead: classify work, ask the minimum questions, create tickets, and dispatch without implementing.
to-tickets
Use when breaking a plan into tracer-bullet GitHub issues with blocking edges.
swarm-swarm
Self-claiming pool orchestration. Workers race to claim tasks from a shared pool, loop until the pool is empty.
build-flow
Autonomously build a complete Power Automate flow from a description. Use when you need to generate a full flow definition and create it.
add-azuredevops
Adds Azure DevOps connector to a Power Apps code app. Use when querying work items, creating bugs, managing pipelines, or making ADO API calls.