Compozy is a system for coordinating AI coding agents, allowing command-line agents to divide work, exchange tasks, run scheduled or repeated jobs, and share project memory under browser supervision. Developers and technical operators use it to create, automate, and monitor ongoing agent work. The catalogue entries provide skills and other add-ons for its agent workflows.
Borrowing it
Nothing to install: this file belongs to compozy/compozy. 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/compozy/compozy/main/.agents/skills/eng/eng-real-scenario-qa/SKILL.mdgit clone --depth 1 https://github.com/compozy/compozyWrote 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/compozy/compozy/eng-real-scenario-qa)<a href="https://agentmods.dev/skills/compozy/compozy/eng-real-scenario-qa"><img src="https://agentmods.dev/badge/skills/compozy/compozy/eng-real-scenario-qa.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00056 | $0.03174 |
| Opus 5 | $0.00028 | $0.01587 |
| Sonnet 5 | $0.00011 | $0.00635 |
| Haiku 4.5 | $0.00006 | $0.00317 |
Grade A, and why
eng-real-scenario-qa 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 2d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Real Scenario QA
Execute release-grade QA by running an entire fictional startup project on the Compozy runtime and observing the result. The runtime drives the work; the observer never tells agents they are being evaluated. The auditor enforces real deliverables (compiled/parsed/runnable artifacts) and real collaboration (peer messages, review cycles, disagreement resolution).
The skill rejects any prompt that frames the work as QA. See references/forbidden-prompt-phrases.md.
Required Inputs
- playbook-ref (optional): Slug of the playbook to run (e.g.,
northstar-pay,devtool-oss-launch,consumer-saas-growth). When omitted, rotate from the previous run'sPLAYBOOK_REFrecorded inbootstrap-manifest.json.
Procedures
Step 1: Select the Playbook
- Read
.agents/skills/eng/eng-real-scenario-qa/references/playbook-catalog.mdin full. - Resolve the playbook ref:
- If the user supplied a slug, validate it exists at
references/playbooks/<slug>.md. - Otherwise, list
references/playbooks/*.md(excludingREADME) and rotate from the previousPLAYBOOK_REF.
- If the user supplied a slug, validate it exists at
- Record
PLAYBOOK_REF.
Done when: one valid playbook is selected and differs from the previous run when rotation applies.
Step 2: Bootstrap the Lab With the Playbook
- Activate
eng-qa-bootstrapwith scenario$PLAYBOOK_REFand--playbook "$PLAYBOOK_REF"; follow its setup, handoff, and continuation contract (Steps 1–4). Keep the lab alive for execution; bootstrap Step 5 runs at this workflow's terminal teardown. - Consume the canonical
BOOTSTRAP_MANIFESTand its emitted paths. Never reconstruct provider, browser, proxy, audit, or teardown state here. - Confirm the selected playbook, agent registrations, open-task tree, knowledge files, required deliverables/collaboration, and populated charter all belong to the same healthy manifest. Register only
RUNTIME_WORKSPACE_PATHwith Compozy, and capture the returned public id asRUNTIME_WORKSPACE_ID; agents must not see the lab'sqa-artifacts/or audit contracts.
What ships with it
20 files 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.
- assets/operator-kickoff-template.md 2.1 KB
- references/charter.schema.json 3.6 KB
- references/forbidden-prompt-phrases.md 3.4 KB
- references/playbook-catalog.md 3.1 KB
- references/playbook-schema.json 7.1 KB
- references/playbooks/consumer-saas-growth.md 16 KB
- references/playbooks/devtool-oss-launch.md 16 KB
- references/playbooks/northstar-pay.md 26 KB
- references/scenario-contract.schema.json 3.2 KB
- scripts/activate-playbook-tasks.py 13 KB runs code
- scripts/audit-qa-evidence.py 39 KB runs code
- scripts/init-scenario-workspace.sh 839 B runs code
- scripts/observe-runtime.py 22 KB runs code
- scripts/playbook_loader.py 16 KB runs code
- scripts/post-operator-kickoff.py 7.0 KB runs code
- scripts/record-scenario-action.py 5.5 KB runs code
- scripts/seed-playbook-workspace.py 10 KB runs code
- scripts/test_activate_playbook_tasks.py 3.5 KB runs code
- scripts/test_observe_runtime.py 19 KB runs code
- scripts/validate-playbook.py 2.4 KB runs code
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.
- 2d ago Changed 8dd97530aea8
- 7d ago First seen · 118 lines · 56 tokens per session scan A c918dd7c5092
eng-real-scenario-qa is a skill published in the GitHub repository compozy/compozy (2,726 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 3,174 once invoked, about $0.0003 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
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
pyats-dynamic-test
Generate and execute deterministic pyATS aetest validation scripts - interface state, OSPF neighbors, BGP paths, ping matrices, and custom compliance tests. Use when writing a network test, validating post-change state, running pass/fail checks, or building automated regression tests.
trailblaze
Use when working with Trailblaze — natural-language device control for coding agents across iOS, Android, and web, with replayable .trail.yaml files as the artifact. Trigger on mentions of Trailblaze, the trailblaze CLI, .trail.yaml files, trailmaps, waypoints, or requests to drive / author / debug / run UI tests on…
Detox Mobile Testing
Gray-box end-to-end testing for React Native apps with Detox. Covers .detoxrc.js configuration, build and test commands, matchers, device.launchApp control, automatic synchronization, and macOS CI pipelines.