Borrowing it
Nothing to install: this file belongs to cyanseek/dsh-native-playbook. 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/cyanseek/dsh-native-playbook/main/AGENTS.mdgit clone --depth 1 https://github.com/cyanseek/dsh-native-playbookWrote 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/instructions/cyanseek/dsh-native-playbook/agents-md)<a href="https://agentmods.dev/instructions/cyanseek/dsh-native-playbook/agents-md"><img src="https://agentmods.dev/badge/instructions/cyanseek/dsh-native-playbook/agents-md/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/instructions/cyanseek/dsh-native-playbook/agents-md"><img src="https://agentmods.dev/badge/instructions/cyanseek/dsh-native-playbook/agents-md.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 | $0.00919 | $0.00919 |
| Opus 5.5 | $0.00368 | $0.00368 |
| Sonnet 5.5 | $0.00184 | $0.00184 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
dsh-native-playbook AGENTS.md 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository guidance
Goal
Map a user's task to the most appropriate native DeepSeek Harness capability before recommending an external plugin or custom workaround.
Non-goals
- Do not become a third-party plugin registry.
- Do not mirror all upstream documentation.
- Do not add plugin-only resolver logic; the runtime adapter must call the shared resolver.
- Do not collect telemetry.
Repository map
catalog/task-map.yml: curated task-to-capability mappings.generated/: deterministic facts generated from one official upstream commit.activation-recipes/: reviewed, version-gated, reversible native activation recipes.skills/dsh-native-playbook/: concise Skill plus focused references..codex-plugin/plugin.json: thin Codex skill-only plugin adapter overskills/.cordis.patch.yml: installable DSH bundle layer for the runtime adapter.src/: shared resolver, profile inspector, installer, CLI, API, and thin DSH adapter.scripts/: upstream sync and repository validation.tests/: behavior, profile, installer, and Skill contract tests.
Source-of-truth hierarchy
- Current official DeepSeek Harness source files pinned in
generated/upstream.json. - Effective profile output from
dsh --profile <name> --dump-config. - Curated intent and fallback policy in
catalog/task-map.yml. - Human-facing explanations in the Skill and READMEs.
Package existence alone is never evidence that a capability is ready.
Generated and curated files
- Never hand-edit
generated/upstream.jsonorgenerated/UPSTREAM_COMMIT. - Run
pnpm sync:upstreamto update generated facts. - Never let upstream sync rewrite
catalog/task-map.ymlor hand-authored recipes. - A task-map reference to a removed upstream tool must fail validation.
Commands
pnpm lint
pnpm typecheck
pnpm test
pnpm build
pnpm validate:skill
pnpm validate:plugin
pnpm validate:dsh-plugin
pnpm verify:upstream
pnpm smoke:json
pnpm smoke:consumer
pnpm metrics
Run the complete set before release. Use pnpm sync:upstream -- --source-dir <checkout>
when validating against a trusted local upstream checkout.
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 · 98 lines · 919 tokens per session scan A 8a0a715f5d22
dsh-native-playbook AGENTS.md is an instructions file published in the GitHub repository cyanseek/dsh-native-playbook (4 stars, last pushed 1mo ago), licensed MIT. It adds 919 tokens to every session, about $0.0037 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 2026-08-31.
dsh-native-playbook AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dsh-native-playbook AGENTS.mdcyanseek/dsh-native-playbook | Instructions file | 4 | 1mo ago | MIT | A | 919 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |