Borrowing it
Nothing to install: this file belongs to acaprino/daodan. 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/acaprino/daodan/master/.agents/skills/downstream-exports/SKILL.mdgit clone --depth 1 https://github.com/acaprino/daodanWrote 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/acaprino/daodan/downstream-exports)<a href="https://agentmods.dev/skills/acaprino/daodan/downstream-exports"><img src="https://agentmods.dev/badge/skills/acaprino/daodan/downstream-exports/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/acaprino/daodan/downstream-exports"><img src="https://agentmods.dev/badge/skills/acaprino/daodan/downstream-exports.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 | $0.00159 | $0.07424 |
| Opus 5.5 | $0.00064 | $0.02970 |
| Sonnet 5.5 | $0.00032 | $0.01485 |
| Haiku 4.5 | $0.00016 | $0.00742 |
Grade A, and why
downstream-exports 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 9d 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 — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Downstream exports
[!WARNING] This skill is a maintenance method, not the workflow executor. Apply shared fixes to kernels, adapters or compiler source and regenerate all five hosts; never patch generated exports. Review the entire loaded instruction closure, including nested references, role resources and a single isolated worker. Verify actual tool/input schemas, skill/agent/workflow identities, model and permission bindings, active-host dependencies, browser stop/stdin behavior, and output helper/contract/result-reader agreement. Agents and coordinators execute and verify; the harness owns its supported continuation and state. Turn end alone does not prove delivery; an empty child requires inspection or recovery before the expected delivery can be accepted. Report registration, rendering/adaptation tests, installed-host probes and live workflow results separately. A digest or a green manifest check cannot replace the affected operational checks.
The mirror image of the external-repo-intake skill. That skill covers content flowing in from other repos; this one covers our content flowing out to the other hosts.
Nothing under exports/ is edited by hand, ever. Every file there is compiler output from plugins/ plus adapters/, and python scripts/daodan_build.py --check fails the build the moment a committed package stops reproducing from its source. If an export looks wrong, the bug is in the kernel, the adapter, or the compiler. Fixing the export directly produces a change that the next build silently deletes.
The split that decides where a change goes
The core owns roles, workflow dependencies, required context isolation, joins and observable contracts. A harness owns host APIs, dispatch, scheduling, retries and result collection.
| The change is about | It belongs in |
|---|---|
| what a reviewer looks for, what a workflow means, what a report must contain | plugins/<name>/ (Markdown for behaviour, TOML for structure) |
| which host tool satisfies a neutral capability | adapters/<host>/capabilities.toml |
| which coordination strategies a host supports, and in what order | adapters/<host>/coordination.toml |
| where a component lands in a host's package | adapters/<host>/layout.toml |
| the wrapper text that tells a host harness how to dispatch | adapters/<host>/templates/ |
| how one host enforces a neutral policy | adapters/<host>/policies/<name>/ with policy.toml naming what it implements |
| a meaning that genuinely cannot be rendered from the generic templates | adapters/<host>/overrides/<plugin>/<workflow>/ |
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.
- 9d ago Changed · +2 lines 3ac2095cb022
- 12d ago Changed 1638195a1759
- 13d ago Changed d281c7ddcf6c
- 18d ago Changed · +7 lines 25f2d648bfb3
- 23d ago Changed cb9f74ef979e
- 24d ago Changed · +2 lines 447decbbc74f
- 25d ago Changed · +1 lines 5a480a5bb363
- 26d ago Changed · +78 lines 63b3cf8c66d5
- 29d ago Changed · +8 lines c78ed14ca46b
- 1mo ago First seen · 274 lines · 159 tokens per session scan A edf968795aae
downstream-exports is a skill published in the GitHub repository acaprino/daodan (9 stars, last pushed 4d ago), licensed MIT. It adds 159 tokens to every session and 7,424 once invoked, about $0.0006 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.
downstream-exports compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| downstream-exportsacaprino/daodan | Skill | 9 | 4d ago | MIT | A | 159 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |