Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/getaero-io/gtm-eng-skillsnpx agentmods add skills/getaero-io/gtm-eng-skills/deepline-playsWrote 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/getaero-io/gtm-eng-skills/deepline-plays)<a href="https://agentmods.dev/skills/getaero-io/gtm-eng-skills/deepline-plays"><img src="https://agentmods.dev/badge/skills/getaero-io/gtm-eng-skills/deepline-plays/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/getaero-io/gtm-eng-skills/deepline-plays"><img src="https://agentmods.dev/badge/skills/getaero-io/gtm-eng-skills/deepline-plays.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 28 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.02388 |
| Opus 5 | $0.00046 | $0.01194 |
| Sonnet 5 | $0.00018 | $0.00478 |
| Haiku 4.5 | $0.00009 | $0.00239 |
Grade A, and why
deepline-plays scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deepline Plays
Quick Start
npm install -g deepline
# Fallback for secure sandboxes: mkdir -p "$HOME/.local" && npm config set prefix "$HOME/.local" && export PATH="$HOME/.local/bin:$PATH" && npm install -g deepline --registry https://code.deepline.com/api/v2/npm/
deepline auth register --wait auto
deepline auth wait --timeout 120 # completes Cowork/browser approval; no-op if already connected
deepline auth status
deepline -h
CLI resolution
Run deepline when it is available. If the shell reports that command is missing, use <workspace-root>/.deepline/runtime/bin/deepline (or the npm-created .cmd shim on Windows). If neither exists, follow https://code.deepline.com/INSTALL.md to set up Deepline.
Debug every Play run: use deepline plays run <file.play.ts> --input '<json>' --debug while iterating, or deepline runs logs <run-id> --debug for an existing run. completed means the runtime finished, not that an external destination accepted the result; the debug logs retain caught non-2xx ctx.fetch responses with their key, method, destination origin, and HTTP status.
Before the first Deepline fanout in a task, run deepline preflight --json as
one standalone command and wait for it to finish. Never submit preflight beside
another Deepline command. After it succeeds, prefix every Deepline command that
may run concurrently with DEEPLINE_SKIP_SELF_UPDATE=1; serial commands may
stay bare.
contract → compare → exploit → recover → export → price
Ordinary TypeScript, no DSL. A SearchProgram is one function that calls a tool,
a fetch, a child Play, a connector, or a local artifact and returns a typed
attempt. runSearchExperiment owns the pilot, ranked waterfall, holdout,
gap-only retries, and cost/coverage report.
Deliverable
| Part | Contents |
|---|---|
| Result line | rows in / accepted / marginal credits per accepted row / run id |
| CSV | the user's exact headers, per-claim source, miss_reason on every null |
| Unresolved rows | in the same file; a null carries an absence receipt |
| Route table | initial and final waterfall, cost and completions per route |
| COST RECEIPT | the block run-and-export-search-experiment.py prints, verbatim |
| Next actions | dormant routes and what each would buy, at measured cost deltas |
What ships with it
43 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.
- jobs/automating.md 4.3 KB
- jobs/enriching.md 22 KB
- jobs/finding.md 21 KB
- jobs/researching.md 13 KB
- plays/account-gtm-research.kernel.play.ts 25 KB runs code
- plays/company-question-research.kernel.play.ts 11 KB runs code
- plays/company-research.kernel.play.ts 17 KB runs code
- plays/company-to-person-experiment.template.ts 11 KB runs code
- plays/named-account-people.kernel.play.ts 18 KB runs code
- plays/research-experiment.example.play.ts 14 KB runs code
- plays/research-kernel.example.play.ts 17 KB runs code
- plays/search-experiment.fixture.play.ts 3.9 KB runs code
- plays/search-experiment.template.ts 5.8 KB runs code
- plays/shared/corroboration.ts 12 KB runs code
- plays/shared/grounded-extraction.ts 9.4 KB runs code
- plays/shared/rerank-cli.ts 14 KB runs code
- plays/shared/rerank.ts 24 KB runs code
- plays/shared/research-experiment.ts 63 KB runs code
- plays/shared/research-kernel.ts 28 KB runs code
- plays/shared/research-portfolio.ts 31 KB runs code
- plays/shared/route-experiment.ts 55 KB runs code
- plays/shared/search-experiment.ts 105 KB runs code
- plays/shared/search-strategy.ts 2.3 KB runs code
- plays/shared/source-plan.ts 8.6 KB runs code
- references/api-reference.md 49 KB
- references/debugging.md 15 KB
- references/sdk-reference.md 96 KB
- scripts/check-search-experiment.py 14 KB runs code
- scripts/cost-receipt.py 15 KB runs code
- scripts/evaluate-source-plan-corpus.ts 8.6 KB runs code
- scripts/init-account-gtm-research-play.sh 456 B runs code
- scripts/init-company-question-research-play.sh 475 B runs code
- scripts/init-company-research-play.sh 444 B runs code
- scripts/init-named-account-people-play.sh 872 B runs code
- scripts/init-research-experiment-play.sh 1.3 KB runs code
- scripts/init-research-play.sh 1.1 KB runs code
- scripts/init-strategy-play.sh 984 B runs code
- scripts/run-and-export-search-experiment.py 9.1 KB runs code
- scripts/scaffold-search-experiment.py 16 KB runs code
- scripts/show-declared-getters.py 4.2 KB runs code
- shared/authoring.md 28 KB
- skill-metadata.json 1.2 KB
- templates/strategy-map.md 2.9 KB
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.
- 4d ago Changed · +24 lines fa2eafa284d8
- 9d ago Changed · +2 lines f2b4cce5f502
- 12d ago First seen · 169 lines · 92 tokens per session scan A f8f9523b76d6
deepline-plays is a skill published in the GitHub repository getaero-io/gtm-eng-skills (58 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 2,388 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 2026-08-30.
Other skills, from other repositories
inbound-lead-enrichment
Fills in missing data for inbound leads — researches the company, identifies the person's role and seniority, finds other stakeholders at the company, checks for existing CRM relationships, and updates the lead record. Produces enriched lead data ready for qualification or outreach. Tool-agnostic.
inbound-lead-qualification
Qualifies inbound leads against full ICP criteria — company size, industry, use case fit, role/seniority of the person. Checks CRM and existing customer base for duplicates and existing relationships. Outputs a scored CSV with qualification status, reasoning, and pipeline overlap flags. Tool-agnostic — works with any…
inbound-lead-triage
Triages all inbound leads from a given period — demo requests, free trial signups, content downloads, webinar registrations, chatbot conversations. Classifies by urgency, qualifies against ICP, enriches with context, and produces a prioritized action queue with recommended response for each lead. Tool-agnostic — works…
company-contact-finder
Find decision-makers at a specific company using Apollo, Crustdata, Fiber, and PDL people search via Gooseworks MCP. Given a company name and target titles, returns a list of contacts with name, title, LinkedIn URL, and location.
job-scraper
Search for job postings across LinkedIn and Indeed. Use when users want to find open roles, monitor hiring signals, identify companies hiring for specific positions, or research competitor hiring activity. Returns job title, company, location, salary, description, seniority level, and direct apply URLs. No login or…
apollo-lead-finder
Two-phase Apollo.io prospecting: free People Search to discover ICP-matching leads, then selective enrichment to reveal emails/phones (credits per contact). Creates Apollo lists. Deduplicates against existing contacts by LinkedIn URL.