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 agentmods add skills/air-gapped/skills/responses-apinpx skills add air-gapped/skills --skill responses-apigit clone --depth 1 https://github.com/air-gapped/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/air-gapped/skills/responses-api)<a href="https://agentmods.dev/skills/air-gapped/skills/responses-api"><img src="https://agentmods.dev/badge/skills/air-gapped/skills/responses-api.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 | $0.00131 | $0.02921 |
| Opus 5 | $0.00066 | $0.01460 |
| Sonnet 5 | $0.00026 | $0.00584 |
| Haiku 4.5 | $0.00013 | $0.00292 |
Grade A, and why
responses-api scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sN http://localhost:8000/v1/responses -H "Content-Type: application/json" \ How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Responses API Reference
The OpenAI Responses API (POST /v1/responses) is the recommended API for
agentic workloads. Launched March 2025. Chat Completions is NOT deprecated,
but superseded for new projects — and since 2026-07-29 OpenAI's own
publications call it "our legacy Chat Completions API".
Sibling protocols in the inference-apis plugin. Backend support for
Responses is far thinner than for chat-completions-api, which remains the
lingua franca every server implements — check that skill before assuming a
target speaks Responses, and for the translation seam when it doesn't. The
Anthropic-protocol equivalent is messages-api. Three protocols, one
question: which surface does this backend actually serve?
Codex CLI dropped Chat Completions in Feb 2026; most major clients (OpenCode, Continue.dev, Cline, Zed, Roo-Code, Vercel AI SDK 5+) now default to Responses. 10 backends serve /v1/responses — Llama Stack is the only non-OpenAI backend that implements /v1/responses/compact; the LiteLLM gateway exposes the route too (PR #18697, since 2026-01-06) but as pure passthrough — it only works when the upstream provider supports compaction. Full adoption timeline and per-client status in references/adoption.md.
Last refreshed: 2026-07-31.
Key Differences from Chat Completions
| Aspect | Chat Completions | Responses API |
|---|---|---|
| Input | messages[] with role+content |
input (string or InputItem[]) + instructions |
| Output | choices[0].message |
output[] array of typed OutputItems |
| Tool defs | tools[].function.{name,params} (nested) |
tools[].{type,name,params} (flat, strict:true default) |
| Tool calls | message.tool_calls[].function |
Separate function_call output items |
| Tool results | {"role":"tool","tool_call_id":"..."} message |
{"type":"function_call_output","call_id":"..."} input item |
| State | Client manages full history | Server via previous_response_id OR conversation (Conversations API) |
| Streaming | Single delta event, data-only SSE | 53 typed events (HTTP SSE or WebSocket since 2026-02-23) |
| Built-in tools | None | web_search, file_search, code_interpreter, computer (GA 2026-03-05), MCP, image_gen, shell (2026-02-10), tool_search (2026-03-05) |
| Skills | N/A | Attach via tools[].environment.skills[] inside hosted Shell |
| Reasoning | reasoning_effort top-level |
reasoning: {effort: "none".."xhigh" ("max" on GPT-5.6+), generate_summary} |
| Context mgmt | None | context_management.compact_threshold + compaction output item, or POST /v1/responses/compact |
| Reasoning persistence | Discarded between turns | Kept server-side; pass via previous_response_id or include: ["reasoning.encrypted_content"] |
| Finish | finish_reason string |
response.status + per-item status |
| Prompt caching | prompt_cache_key (same) |
prompt_cache_key + prompt_cache_retention: "in_memory"/"24h" |
| Resume dropped stream | No | GET /v1/responses/{id}?stream=true&starting_after=<seq> |
What ships with it
8 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.
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 First seen · 143 lines · 131 tokens per session scan A 78383edb8143
responses-api is a skill published in the GitHub repository air-gapped/skills (5 stars, last pushed 2d ago), licensed MIT. It adds 131 tokens to every session and 2,921 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
dummy-dataset
Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.
outcome-roadmap
Transform an output-focused roadmap into an outcome-focused one that communicates strategic intent. Rewrites initiatives as outcome statements reflecting user and business impacts. Use when shifting to outcome roadmaps, making a roadmap more strategic, or rewriting feature lists as outcomes.
competitive-battlecard
Create sales-ready competitive battlecards comparing your product against a specific competitor — positioning, feature comparison, objection handling, and win/loss patterns. Use when preparing sales teams, creating competitive materials, or responding to 'why not competitor X?'.
stakeholder-map
Build a stakeholder map using a power/interest grid, identify communication strategies per quadrant, and generate a communication plan. Use when managing stakeholders, preparing for a launch, aligning cross-functional teams, or planning stakeholder engagement.
create-app
Guided journey from a raw app idea to a validated, cleanly architected first version that ships on a sustainable cadence. Orchestrates ten skills phase by phase - lean-startup, design-sprint, clean-architecture, domain-driven-design, clean-code, pragmatic-programmer, system-design, ios-hig-design, 37signals-way…
create-business
Guided journey from raw idea to a validated, positioned, priced business with a chosen beachhead. Orchestrates ten skills phase by phase - jobs-to-be-done, mom-test, design-sprint, lean-startup, good-strategy-bad-strategy, blue-ocean-strategy, obviously-awesome, hundred-million-offers, monetizing-innovation…