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.
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 compozy/compozy --skill cy-orquestrate-issuegit 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/cy-orquestrate-issue)<a href="https://agentmods.dev/skills/compozy/compozy/cy-orquestrate-issue"><img src="https://agentmods.dev/badge/skills/compozy/compozy/cy-orquestrate-issue/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/compozy/compozy/cy-orquestrate-issue"><img src="https://agentmods.dev/badge/skills/compozy/compozy/cy-orquestrate-issue.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 | $0.00092 | $0.01540 |
| Opus 5 | $0.00046 | $0.00770 |
| Sonnet 5 | $0.00018 | $0.00308 |
| Haiku 4.5 | $0.00009 | $0.00154 |
Grade A, and why
cy-orquestrate-issue 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 today.
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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrate Issue Resolution
The orchestrator investigates and dispatches; a dedicated CompozyOS session implements each issue through PR delivery.
Contract and inputs
- Accept issue numbers/URLs or a bug report with screenshots, logs, or reproduction steps. Resolve the repository from the workspace remote; ask only if the target remains ambiguous.
- Default executor: agent
general, providercodex, modelgpt-6-astra, reasoning efforthigh. Explicit user overrides win. Verify the effective runtime; never silently substitute a model. - Create one new managed worktree and new logical session per issue. Follow-ups for that issue go to its recorded session. Never repurpose an unrelated active session.
- An invocation to resolve issues authorizes the scoped issue, branch, push, PR, review replies, and review-remediation work. It does not authorize merge, destructive Git, deleting worktrees, installing reviewers, or changing the user's host runtime. Existing session authorization wins.
- Default orchestration ends after verified dispatch, with the executor responsible for the full delivery contract. If asked to accompany delivery, supervise until that contract is satisfied. A launch report must say in progress, never that the issue is resolved.
1. Load the runtime contract
Use the active harness to resolve compozy__skill_view. Load the Compozy skill and the full
references selected by its router for tools, worktrees, sessions, orchestration, and Goals:
references/tools-and-skills.md, references/native-tools.md, references/worktrees.md,
references/runtime-operations.md, references/tasks-and-orchestration.md, and
references/loops.md. Reuse complete current reads from this session. Follow source-qualified
command_id and retained-result continuation instructions when supplied.
Discover capabilities with compozy__tool_search and inspect live descriptors with
compozy__tool_info. The canonical IDs below are discovery keys, not harness invocation names.
Use the returned references and current schemas. A denied tool/skill read is not permission to
bypass policy through CLI or filesystem access.
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.
- today First seen · 108 lines · 92 tokens per session scan A 0ffe7386af61
cy-orquestrate-issue is a skill published in the GitHub repository compozy/compozy (2,739 stars, last pushed today), licensed MIT. It adds 92 tokens to every session and 1,540 once invoked, about $0.0005 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 2026-09-12.
Other skills, from other repositories
agent-merge-conflict-arbiter
Neutral arbiter for merge conflicts between two agents.
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
bisect
Bisect regressions or broken builds in the Chromium repository using deterministic binary search, checking out midpoint commits, syncing dependencies with gclient sync, compiling the target with autoninja, and querying the user for test results until the culprit commit is isolated.
mantis-critic
Assesses the production viability of findings, filtering out debug-only features and assertion traps. Use when findings have been validated and you need to confirm they are triggerable in production release builds (with assertions disabled). Don't use for writing reproduction scripts or patches.
hotpath_bump
Bump the hotpath version number across the workspace and related files. Updates crate versions in Cargo.toml files (exact patch version) and version references in the backend middleware, hotpathinit skill, and README (major.minor only). Use when the user wants to bump, bump the version, or release a new hotpath…
triaging-merge-queue-failures
Decision procedure for a PR that failed or was removed from the Trunk merge queue: classify the kick (superseded by a newer commit, not mergeable, a gate that failed on a cancelled run, real failure, one-off flake, or repo-wide flaky/infra issue) and take the matching action (wait, hold and fix, requeue once, or…