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 Fly2Kiana/Codex-DSH-Orchestrator --skill codex-dshgit clone --depth 1 https://github.com/Fly2Kiana/Codex-DSH-OrchestratorWrote 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/fly2kiana/codex-dsh-orchestrator/codex-dsh)<a href="https://agentmods.dev/skills/fly2kiana/codex-dsh-orchestrator/codex-dsh"><img src="https://agentmods.dev/badge/skills/fly2kiana/codex-dsh-orchestrator/codex-dsh.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 | $0.00036 | $0.01782 |
| Opus 5 | $0.00018 | $0.00891 |
| Sonnet 5 | $0.00007 | $0.00356 |
| Haiku 4.5 | $0.00004 | $0.00178 |
Grade A, and why
codex-dsh 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 7d 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.
This is a copy
92% identical to claude-code-dsh — 16 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex to DSH collaboration
This skill operates the standalone Codex-side MCP bridge. The repository may be discovered under the broad dsh-plugin ecosystem topic, but it is not a DSH Cordis bundle and must not be installed with dsh plugin --profile ... add ....
Use the dsh_* MCP tools only with the user's already managed official DSH Web Host. The bridge is connect-only: never start, daemonize, stop, or reconfigure dsh web. Do not modify DSH model settings except through the explicit typed routing fields described below; that operation has a disclosed global-default side effect.
Workflow
Before any new delegation, build a compact handoff from already-known progress plus read-only workspace evidence: objective and completed work, Git HEAD/status and changed paths when available, focus code/Markdown paths, relevant tests, constraints, and unresolved issues. Tell DSH to read the focus paths first and avoid a repository-wide scan unless blocked. Never include secrets, raw large diffs, file bodies, caller chat, or internal reasoning. This is caller guidance, not new filesystem authorization; dsh-Agentlink does not receive prior caller conversation state automatically.
- Call
dsh_host_statuswhen Host availability is unknown. If unreachable, report the doctor/start command; do not start the Host yourself. - When the user explicitly identifies an existing DSH Desktop session, call
dsh_find_sessionsand require one intended idle root result. Attach only withdsh_attach_sessionusing the exact returnedsessionIdplus its freshupdatedAt,cwd, and title preconditions. Never attach by title alone or guess an id. Attach creates or reuses bridge-local mapping/claim state and may reconcile history for supervision, but it never returns or persists conversation bodies, prompts DSH, renames the session, or changes its model. After attachment, usedsh_followupwith the compact handoff when work should continue. A routed follow-up uses the same user-priority, semantic-profile, live-catalog validation, re-read verification, and global-default side-effect rules as routed delegation; omit routing to inherit. - Otherwise call
dsh_delegatewith a complete prompt and an existing absolutecwd. The user's explicit route request always wins. Otherwise omit routing to inherit DSH, chooseflashfor routine search/implementation/test repair, andprofor architecture or difficult multi-step debugging. Visual work must declarevisualIntent="required"withcomplexity="low"|"high": low uses the official native Flash Vision; high requires an explicit user choice betweenofficial-flash-visionandmodlens-pro. Do not choose a ModLens profile merely because visual evidence is needed. The bridge's automatic ModLens Flash fallback is limited to one attempt after bounded retries caused only by timeout, unreachable Host, or HTTP 5xx; when the visual policy fields are omitted, preserve an explicitly supplied legacymodelProfile="modlens-flash"for compatibility, but never treat it as the default visual route. AreasoningEffortmust be advertised by the selected catalog model. For ModLens, include DSH-accessible absolute image paths in the text prompt; the bridge does not upload image bytes. Add a conciseselectionReasonwhen choosing autonomously. Explicit routing callssession.selectModel, which on DSH rc.6 also persists the selection as the global default for later sessions; inspect the returned warning and do not select explicitly when that side effect is unacceptable. Normally omitagentPreset; the bridge's installation-time default owns that choice.agentPresetchooses DSH agent composition, not workspace ownership or verified sandbox policy. The shippedcodepreset keeps the standard capability set through DSH Code Mode and is the preferred default for implementation or multi-step tool work. Use the defaultexclusive-writeworkspace claim for edits, preferably on a dedicated git worktree; useread-onlyonly as a bridge-local cooperative claim for tasks that should not mutate files. It does not make DSH run in a read-only filesystem sandbox. Keep the returned BridgeTask id and root session id. - Treat BridgeTask, root session, and turn as distinct. A completed turn can be followed by another turn in the same root session.
- Use
dsh_waitfor at most 30 seconds, thendsh_tailwithnextCursor. Do not poll raw per-session seq values or assume muxsinceresumes history. - Before a write, retain the latest task
cursorand connectionrevision, then pass them assinceCursorandexpectedRevision. Inspectstale_viewchanges instead of blindly retrying. For the same known BridgeTask, usedsh_followup(mode="queue")for a later turn andmode="steer"only when guidance must enter the active turn's next step. Across caller tasks, never guess an old task id; start a fresh delegation when the matching BridgeTask id is not known and the user did not explicitly identify an existing DSH session. - Inspect
dsh_status.pendingInteractions.dsh_followupis not an answer channel. - Answer questions only with
dsh_answer_questionand the exact pending request id/typed answers. Never infer sensitive credentials, publishing, or release answers. - Treat every approval as sandbox escalation. Never auto-allow. Never auto-approve. Use
dsh_resolve_approval(..., outcome="allow_once")only after the supervising user/Codex approval boundary;rejectis the fail-closed response. - Use
dsh_cancel(scope="turn")to cancel only the active turn while preserving queue. Usescope="queue"only with a current queue snapshot and expect a non-atomic per-item result. - Independently inspect DSH-produced files and test evidence before accepting the work. When collaboration is over, call
dsh_release_workspace; this does not close the DSH session.
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.
- 7d ago First seen · 42 lines · 36 tokens per session scan A abb364c8cdbe
codex-dsh is a skill published in the GitHub repository Fly2Kiana/Codex-DSH-Orchestrator (1 stars, last pushed 4d ago), licensed MIT. It adds 36 tokens to every session and 1,782 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to claude-code-dsh, differing in 16 lines, and is treated as a copy.
Other skills, from other repositories
claude-code-dsh
Delegate bounded work from Claude Code to the user's existing official DSH Web Host while preserving typed supervision, task cursors, follow-up, and safe cancellation.
codex-dsh
Delegate bounded work from Codex to the user's existing official DSH Web Host while preserving typed supervision, task cursors, follow-up, and safe cancellation.
dsh-web-skin-developer
Build a new skin for the dsh-web skin collection (DSH Web GUI) and publish it into the Skin Center — the first-level settings section — scaffold with scripts/dsh-skin-new, author the v2 skin.json manifest plus skin.css token remap (pure asset directory, no package.json, no build step), validate with scripts/dsh-skin…
dsh-sdk-upgrade
Safely select and install a compatible official @deepseek-ai SDK release for dsh plugin projects (dsh-web, dsh-trading, and similar monorepos) from npm using an isolated worktree, explicit cohort review, CI-equivalent validation, and controlled rollout — including syncing the project's declared DSH host-version floor…
dsh-web-sdk-compatibility
Adapt and repair dsh-web after an approved official @deepseek-ai SDK/runtime cohort is selected or installed. Compare public API, type, service-injection, module-table, protocol, and behavior changes; map every change to repository consumers; implement the smallest fixes and durable compatibility contracts; handle…
stage-plan
How to turn "here is my material + here's the video I want" into a single, inspectable plan that spans reference images, reference videos, deterministic editing, semantic editing, generation, and composition. The output is project/plan.json — a cross-modal Edit Decision List (EDL) — which the assembler walks.…