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 ABilenduke/copilot-developer --skill feedbackgit clone --depth 1 https://github.com/ABilenduke/copilot-developerWrote 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/abilenduke/copilot-developer/feedback)<a href="https://agentmods.dev/skills/abilenduke/copilot-developer/feedback"><img src="https://agentmods.dev/badge/skills/abilenduke/copilot-developer/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/abilenduke/copilot-developer/feedback"><img src="https://agentmods.dev/badge/skills/abilenduke/copilot-developer/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 | $0.00058 | $0.01649 |
| Opus 5.5 | $0.00023 | $0.00660 |
| Sonnet 5.5 | $0.00012 | $0.00330 |
| Haiku 4.5 | $0.00006 | $0.00165 |
Grade A, and why
feedback scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feedback Skill
Purpose
This skill handles the review cycle after /execute creates a PR. It reads PR comments, creates an immutable feedback.md record in the story directory, applies fixes, and updates the PR. The feedback document is a permanent historical record of what was raised and how it was resolved.
Pipeline position: /execute → PR created → reviewer comments → /feedback → feedback.md + PR updates → merge → Done
First Steps
When this skill is invoked:
- Read the template:
templates/feedback-template.md - Identify the PR:
- If the user specified a PR number, use that
- If on a feature branch, check for an open PR:
~/.local/bin/gh pr list --head "$(git branch --show-current)" \ --repo ABilenduke/content-engine --json number,title --jq '.[0]' - If no PR found, ask the user for the PR number
- Read PR details:
~/.local/bin/gh pr view {number} --repo ABilenduke/content-engine \ --json title,body,reviews,comments,reviewDecision - Locate the story directory: Find the story that produced this PR by:
- Checking the PR description for story document paths
- Checking the branch name for feature/story naming
- Asking the user if neither works
- Read existing story documents: Load plan.md and design.md for context on what was intended
- Read PR review comments:
# General PR comments ~/.local/bin/gh pr view {number} --repo ABilenduke/content-engine --comments # Inline code review comments ~/.local/bin/gh api repos/ABilenduke/content-engine/pulls/{number}/comments \ --jq '.[] | {path: .path, line: .line, body: .body, user: .user.login}' # Review summaries ~/.local/bin/gh api repos/ABilenduke/content-engine/pulls/{number}/reviews \ --jq '.[] | {state: .state, body: .body, user: .user.login}' - Begin processing feedback
Process
Phase 1: Gather & Categorize Feedback
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 179 lines · 58 tokens per session scan A 47b561d1364f
feedback is a skill published in the GitHub repository ABilenduke/copilot-developer (4 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 1,649 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…