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 reem-sab/tech-writer-prompts --skill api-ref-skeletongit clone --depth 1 https://github.com/reem-sab/tech-writer-promptsWrote 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/reem-sab/tech-writer-prompts/api-ref-skeleton)<a href="https://agentmods.dev/skills/reem-sab/tech-writer-prompts/api-ref-skeleton"><img src="https://agentmods.dev/badge/skills/reem-sab/tech-writer-prompts/api-ref-skeleton/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/reem-sab/tech-writer-prompts/api-ref-skeleton"><img src="https://agentmods.dev/badge/skills/reem-sab/tech-writer-prompts/api-ref-skeleton.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 | $0.00113 | $0.00898 |
| Opus 5.5 | $0.00045 | $0.00359 |
| Sonnet 5.5 | $0.00023 | $0.00180 |
| Haiku 4.5 | $0.00011 | $0.00090 |
Grade A, and why
api-ref-skeleton 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.
API Reference Skeleton
Turns an OpenAPI spec into a reference page draft, one section per operation, with a description, a parameter table, request body notes, and a response table. It marks every place the spec does not say enough to write from with an explicit > TODO: line instead of inventing content.
Inputs
{{SPEC}}: An OpenAPI spec (JSON or YAML), complete or partial.
How to apply
Substitute each {{PLACEHOLDER}} above with the user's actual content, then
follow the prompt below exactly — including its output format and its stated
limits.
You are drafting an API reference page from an OpenAPI spec. Your job is to structure and phrase what's in SPEC clearly — not to invent behavior, constraints, or examples the spec doesn't state.
For every operation (path + method) in SPEC, in the order they appear, produce a section in this exact shape:
## `<METHOD> <path>`
<one- to two-sentence description, drawn from the spec's summary/description
fields. If both are missing, write:
> TODO: spec has no summary or description for this operation.>
### Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
<one row per parameter. If a parameter has no description in the spec,
put "> TODO: no description in spec" in the Description cell instead of
inventing one.>
### Request body
<if the operation has a request body, describe its shape and content type
from the schema. If the schema has no description, name the fields and
types you can see and mark undocumented fields individually with a TODO.
Omit this section entirely if the operation has no request body.>
### Responses
| Status | Description | Notes |
|---|---|---|
<one row per response defined in the spec. If a response has no
description, use "> TODO: no description in spec". If the spec defines no
error responses (4xx/5xx) at all for an operation that plausibly has them,
add a closing line: "> TODO: spec defines no error responses for this
operation.">
What ships with it
4 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.
- 2mo ago First seen · 98 lines · 113 tokens per session scan A 84577211d627
api-ref-skeleton is a skill published in the GitHub repository reem-sab/tech-writer-prompts (4 stars, last pushed 2mo ago), licensed MIT. It adds 113 tokens to every session and 898 once invoked, about $0.0005 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.
api-ref-skeleton compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| api-ref-skeletonreem-sab/tech-writer-prompts | Skill | 4 | 2mo ago | MIT | A | 113 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 69k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | 2d ago | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | 2d ago | MIT | A | 46 | Claude Code |
| dev-runtimelangwatch/langwatch | Skill | 5.0k | today | Apache-2.0 | A | 172 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 555 | 5d ago | MIT | A | 105 | Claude Code, Codex |
| migrate-segw-to-raparc-mcp/arc-1 | Skill | 253 | yesterday | MIT | A | 106 | Claude Code |