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 alonf/specrew --skill copilot-launch-contract-divergencegit clone --depth 1 https://github.com/alonf/specrewWrote 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/alonf/specrew/copilot-launch-contract-divergence)<a href="https://agentmods.dev/skills/alonf/specrew/copilot-launch-contract-divergence"><img src="https://agentmods.dev/badge/skills/alonf/specrew/copilot-launch-contract-divergence.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 5.1 | $0.00023 | $0.00522 |
| Opus 5 | $0.00012 | $0.00261 |
| Sonnet 5 | $0.00005 | $0.00104 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
copilot-launch-contract-divergence 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 3d 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
Context
Use this when specrew start changes how it launches Copilot across Windows and Linux/macOS. The runtime contract is not symmetric: the same Copilot CLI flags can keep Windows interactive while breaking Linux/macOS, so launch code, user messaging, tests, and evidence must move together.
Patterns
- Keep
-ibootstrap auto-load on every platform. - Keep
--autopilotbehavior unchanged and mutually exclusive with--mode interactive. - On Windows non-autopilot launches, add
--mode interactive; add--allow-allonly when explicitly allowed. - On Linux/macOS non-autopilot launches, pass
--agent,--add-dir, and-iwithout--mode interactiveor--allow-all, and warn users to expect approval prompts for bootstrap file reads. - When the launch contract changes, update
scripts\\specrew-start.ps1,tests\\integration\\start-command.ps1, andspecs\\019-specrew-distribution-module\\test-evidence\\us5-cross-platform.mdtogether.
Examples
- Feature 019 R13: Windows kept
--mode interactiveto hold the REPL open, while Linux/macOS dropped it because Copilot CLI v1.0.48 already defaults the-iflow into the REPL there and exits one-shot when--mode interactiveis added. pwsh -NoProfile -File tests\\integration\\start-command.ps1is the regression proof for Windows-side launch composition after these changes.
Anti-Patterns
- Assuming Windows and Linux/macOS need the same
copilot --agent ... -iflags. - Changing launch flags without updating runtime messaging and evidence.
- Re-introducing
--allow-allor--mode interactiveon Linux/macOS without fresh live evidence that the CLI behavior changed.
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.
- 3d ago First seen · 34 lines · 23 tokens per session scan A 95d310a0bc92
copilot-launch-contract-divergence is a skill published in the GitHub repository alonf/specrew (54 stars, last pushed 5d ago), licensed MIT. It adds 23 tokens to every session and 522 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 2026-09-03.
Other skills, from other repositories
migrate-xunit-to-xunit-v3
Migrate .NET test projects from xUnit.net v2 to xunit.v3 and fix v3 breaks. Use for package/CPM conversion, OutputType=Exe, preserving the VSTest or MTP runner (including projects currently using YTest.MTP.XUnit2), incompatible TFMs, async void tests, string-to-Type attributes, custom Fact/Theory/BeforeAfterTest…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.
restore-internals-seams-in-finally-blocks-after-each-test
When delegating a task affected by this skill, include.
mobiai-ios-testing
Use when writing or running tests in an iOS project — unit tests, UI tests, snapshot tests, choosing the right framework.
testing-llm
LLM and AI testing patterns — mock responses, evaluation with DeepEval/RAGAS, structured output validation, and agentic test patterns (generator, healer, planner). Use when testing AI features, validating LLM outputs, or building evaluation pipelines.