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 apostl-dev/apostl-skills --skill agent-native-experiencegit clone --depth 1 https://github.com/apostl-dev/apostl-skillsWrote 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/apostl-dev/apostl-skills/agent-native-experience)<a href="https://agentmods.dev/skills/apostl-dev/apostl-skills/agent-native-experience"><img src="https://agentmods.dev/badge/skills/apostl-dev/apostl-skills/agent-native-experience.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 | $0.00119 | $0.02512 |
| Opus 5 | $0.00060 | $0.01256 |
| Sonnet 5 | $0.00024 | $0.00502 |
| Haiku 4.5 | $0.00012 | $0.00251 |
Grade A, and why
agent-native-experience 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 8d 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Native Experience
Turn one product/docs prompt into an honest local assessment and, only with explicit approval, an Apostl execution proof.
Contract
Require:
- target docs or product URL;
- selected quickstart or journey;
- observable activation event promised by that journey.
Accept optionally: product API/OpenAPI, repository path, llms.txt sources,
versioned market/competitor/buyer evidence, human observations, business
metrics/owners, corpus exclusions, and a desired local/sample/full mode.
Return one report using report-contract.md. Always distinguish static evidence, agent runtime evidence, human evidence, and unknown/not-run work. Never turn a fetch, signup, HTTP 200, workaround, or high score into activation proof.
Run the workflow
-
State the journey, target agent/user, activation event, environment, mode, and plausible business consequence. Label unmeasured impact as a hypothesis with the metric and owner needed to validate it.
-
Read rubric.v1.json and sources.v1.json. Refresh drift-prone sources before calling guidance current; record URL, retrieval time, and version or commit.
-
Inventory
llms.txt,llms-full.txt, sitemaps, navigation, API specs, and supplied sources. Canonicalize URLs, record redirects/auth/exclusions and content hashes, then freeze the corpus before full execution. -
Run local non-mutating checks. Use AFDocs directly when available and retain its status/dependency semantics. When AFDocs is unavailable, read local-evidence-collector.md and run the bundled bounded collector:
python3 scripts/collect_evidence.py \ --url https://example.com/docs/quickstart \ --journey "Install and run the quickstart" \ --activation-event "Rendered result is visible" \ --mode sample \ --output-dir ./agent-native-evidence
What ships with it
26 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.
- agents/openai.yaml 229 B
- evals/synthesis-eval.jsonl 1.1 KB
- references/apostl-api.md 5.5 KB
- references/friction-taxonomy.md 805 B
- references/local-evidence-collector.md 6.0 KB
- references/report-contract.md 3.2 KB
- references/rubric.v1.json 14 KB
- references/sources.v1.json 3.9 KB
- routing-eval.jsonl 3.4 KB
- scripts/apostl_client.py 45 KB runs code
- scripts/audit.py 29 KB runs code
- scripts/collect_evidence.py 44 KB runs code
- scripts/evaluate.py 3.2 KB runs code
- scripts/execute_cleanroom.py 11 KB runs code
- scripts/safety.py 2.8 KB runs code
- tests/fixtures/public-artifacts/report.pdf 439 B
- tests/fixtures/public-artifacts/terminal-run.json 458 B
- tests/fixtures/w3schools-clean-room/browser-snapshot.json 181 B
- tests/fixtures/w3schools-clean-room/clean-room-trace.pass.json 1.6 KB
- tests/fixtures/w3schools-clean-room/index.html 211 B
- tests/fixtures/w3schools-clean-room/sha256-inventory.json 180 B
- tests/fixtures/w3schools-clean-room/source-fixture.html 211 B
- tests/test_audit.py 27 KB runs code
- tests/test_client.py 35 KB runs code
- tests/test_collect_evidence.py 16 KB runs code
- tests/test_execute_cleanroom.py 5.1 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.
- 8d ago First seen · 219 lines · 119 tokens per session scan A 08c0482f6ce4
agent-native-experience is a skill published in the GitHub repository apostl-dev/apostl-skills (2 stars, last pushed 9d ago), licensed MIT. It adds 119 tokens to every session and 2,512 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
developer-marketing-playbook
Complete developer marketing playbook covering DevRel programs, documentation as marketing, API developer experience, community building, and hackathon strategy. For dev-tool founders who need to reach engineers. Follow @WeiYipei on X.
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…
add-matrix
Add Matrix channel integration via Chat SDK. Works with any Matrix homeserver.
add-resend
Add Resend (email) channel integration via Chat SDK.