Borrowing it
Nothing to install: this file belongs to DamianEdwards/copilotd. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/DamianEdwards/copilotd/main/.github/skills/copilotd-e2e-verification/SKILL.mdgit 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/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/damianedwards/copilotd/copilotd-e2e-verification"><img src="https://agentmods.dev/badge/skills/damianedwards/copilotd/copilotd-e2e-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 36 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 36 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00031 | $0.01756 |
| Opus 5.5 | $0.00012 | $0.00702 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 (60 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 1,756 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
test-pr-e2e
Test a PR or MR like a human QA engineer using Playwright MCP. Analyzes the diff (or diffs, for a multi-service/microservice feature spanning several PRs) to generate a scenario list (Phase 1), then executes each scenario live in a browser with inline logging and screenshots (Phase 2). Use when asked to "test this PR…
playwright-visual-testing
Add, repair, or review Playwright visual regression tests for browser-facing .NET apps, including screenshot baselines, Pixelmatch thresholds, deterministic rendering, and GitHub Actions artifacts. USE FOR: toHaveScreenshot, page.screenshot visual checks, Pixelmatch/pngjs comparison scripts, visual baseline updates…
kb-github-a11y-scanner
Reference data, not a reviewer. Integrate GitHub Accessibility Scanner. Detects configuration, parses scanner issues, correlates with local scans, and tracks Copilot-assigned fixes.
ui-aqa-flow
Workflow for automated QA: integration and end-to-end UI test automation, page objects, etc.
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.
playwright-testing
Generer og kjør Playwright E2E-tester for webapplikasjoner med page objects, auth fixtures og tilgjengelighetstester.