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 skills/damianedwards/copilotd/copilotd-e2e-verificationnpx skills add DamianEdwards/copilotd --skill copilotd-e2e-verificationgit clone --depth 1 https://github.com/DamianEdwards/copilotdWrote 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/damianedwards/copilotd/copilotd-e2e-verification)<a href="https://agentmods.dev/skills/damianedwards/copilotd/copilotd-e2e-verification"><img src="https://agentmods.dev/badge/skills/damianedwards/copilotd/copilotd-e2e-verification.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.01756 |
| Opus 5 | $0.00015 | $0.00878 |
| Sonnet 5 | $0.00006 | $0.00351 |
| Haiku 4.5 | $0.00003 | $0.00176 |
Grade A, and why
copilotd-e2e-verification 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 4d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
copilotd end-to-end verification
Use this skill when validating substantial copilotd orchestration changes, especially changes to dispatch rules, reconciliation, session lifecycle, worktree handling, prompt callbacks, or GitHub issue/PR feedback loops.
Goal
Verify copilotd as a live reconciliation daemon, not just by build or command smoke tests. A good verification proves that real GitHub issues and pull requests move through the expected lifecycle, Copilot sessions can call back into copilotd, worktrees and state converge correctly, and temporary artifacts are cleaned up.
Optimum approach
- Use an isolated copilotd home. Set
COPILOTD_HOMEto a disposable directory such as.\copilotd-home-e2eor another task-specific path. Do not use the user's normal~\.copilotdstate. - Start with local CLI validation. Build the branch, then verify
config,rules add/list/update/delete, invalid rule arguments,status,session list --all, and JSON persistence before creating live artifacts. - Use a real but safe target repository. Prefer a repo already cloned locally and writable by the user. Configure
repo_homeso copilotd resolves the existing clone and creates sibling<repo>_sessionsworktrees. - Create explicit temporary labels. Use unique labels such as
copilotd-e2e-ready,copilotd-e2e-clarify, andcopilotd-e2e-prso rules match only the verification artifacts. - Create at least two issue scenarios.
- A ready-to-implement issue with small, deterministic acceptance criteria that should lead to a branch, commit, PR,
session pr, andWaitingForReview. - An intentionally ambiguous issue that should lead to
session comment,WaitingForFeedback, a real clarification reply, and re-dispatch.
- A ready-to-implement issue with small, deterministic acceptance criteria that should lead to a branch, commit, PR,
- Create a PR rule that observes the issue-created PRs. Add a PR dispatch rule using
--kind pr, a temporary PR label,--base, and a safe branch strategy such asread-onlyfor validation-only sessions. - Drive the full feedback loop. After issue sessions create PRs, let the PR rule launch PR-root validation sessions. Ensure those sessions comment on the PR. Then add a manual PR comment or review from a trusted user without a copilotd marker so the original issue-owned
WaitingForReviewsession re-dispatches, pushes a follow-up commit, and returns toWaitingForReview. - Observe state and GitHub together. Cross-check
state.json,copilotd session list --all, issue comments, PR comments, PR labels, PR commits, and local git worktrees. Do not trust a single surface. - Keep a journal. Record every issue, workaround, and stop-worthy finding as it happens, including exact issue/PR numbers and whether the behavior was expected or a product problem.
- Clean up aggressively. Close temporary PRs without merging, close temporary issues, delete temporary branches/labels, stop daemon processes, remove isolated homes and temporary publish folders, prune worktrees, and verify the target repo returns to a clean default branch.
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.
- 4d ago First seen · 103 lines · 31 tokens per session scan A 83cea94d48cc
copilotd-e2e-verification is a skill published in the GitHub repository DamianEdwards/copilotd (59 stars, last pushed 7d ago), licensed MIT. It adds 31 tokens to every session and 1,756 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
winui-ui-testing
Automated UI testing for Windows desktop apps — generate a batch test script with the winapp ui UI Automation harness, run all tests in one pass, read results. Covers element assertions, interactions, value checking (TextBox, ComboBox, ToggleSwitch), keyboard shortcuts and typing (send-keys), hover, drag-and-drop…
pr-review
Multi-dimensional review of a PR or feature branch in microsoft/win-dev-skills. Activate on "review my PR / changes / branch", "vet before pushing", "PR review", "is this ready to merge". Fans out parallel sub-agents over skill content, the skill-vs-tool boundary (solution hierarchy), tool correctness…
winui-design
Use when designing, reviewing, or fixing WinUI 3: sample and control discovery with winapp find-ui, layout planning, control choice, Fluent Design alignment, Light/Dark/High Contrast theming, typography, spacing, brushes, accessibility, and XAML data-binding design. Load before authoring new XAML, reviewing UI PRs…
winui-dev-workflow
Build and run workflow for WinUI 3 apps with WinApp CLI 0.6+ — project creation with winapp new, project-mode winapp run, BuildAndRun.ps1 analyzer integration, crash diagnosis, and prerequisites. Use when creating, building, running, or fixing build errors in a WinUI 3 project.
winui-packaging
MSIX packaging, code signing, and distribution for WinUI 3 apps — build for release, certificate generation (winapp cert generate), certificate trust, code signing (winapp sign), self-contained deployment, CI/CD with GitHub Actions, and Microsoft Store submission. Use when preparing for release, creating MSIX…
winui-session-report
Analyze the current or a recent agent session (GitHub Copilot CLI or Claude Code) and generate a diagnostic report. Use only when the user explicitly asks for session feedback, agent debugging, or a review of what happened during a build session. Do not inspect session data automatically.