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/pactflow/pactflow-agent-skills/openapi-parsernpx skills add pactflow/pactflow-agent-skills --skill openapi-parsergit clone --depth 1 https://github.com/pactflow/pactflow-agent-skillsWhat 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 | $0.00145 | $0.01419 |
| Opus 5 | $0.00072 | $0.00709 |
| Sonnet 5 | $0.00029 | $0.00284 |
| Haiku 4.5 | $0.00015 | $0.00142 |
Grade A, and why
openapi-parser 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 2d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenAPI Parser Skill
Reference files
references/schema-patterns.md— how to interpret and enumerate every complex pattern (anyOf / oneOf / allOf / discriminator / $ref / enum / pattern / nullable / optional), with real examples from snyk, digitalocean, posthog, and front/core specsreferences/drift-mapping.md— how to map enumerated schema variants to Drift YAML, including datasets, expressions, lifecycle hooks for stateful cases, and expected response matchers for each pattern type
Workflow
OpenAPI version: This skill targets OpenAPI 3.x. Swagger 2.0 specs use the same structural patterns (
$ref,allOf,oneOf) but different envelope syntax — you may need to adapt field names manually. If working from thekonfig-sdks/openapi-examplescollection, seereferences/example-repos.mdfor navigation commands.
1. Locate the endpoint
Extract only what's needed:
# Find the line number of the endpoint (macOS/Linux/Git Bash/WSL)
grep -n "^ /path/to/endpoint" spec.yaml
# Read just that block (adjust line range as needed)
# Then follow each $ref to components/schemas
grep -n "SchemaName:" spec.yaml
# PowerShell equivalents (Windows)
Select-String -Path spec.yaml -Pattern "^ /path/to/endpoint" | Select-Object LineNumber, Line
Select-String -Path spec.yaml -Pattern "SchemaName:" | Select-Object LineNumber, Line
Extract: path/query/header parameters, request body schema, and each response status code's schema.
2. Resolve $refs recursively
- Grep for
Foo:in the spec to find its definition block - If Foo itself contains refs, resolve those too
- Stop at primitive types (
string,integer,boolean,array,object)
allOf: [$ref: Base, properties: {...}] is inheritance — merge Base fields with local
properties to get the full schema. See references/schema-patterns.md for all patterns.
What ships with it
9 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.
- evals/01-anyof-parameter-variants.json 1.1 KB
- evals/02-discriminator-with-allof.json 1.3 KB
- evals/03-regex-pattern-field.json 1.2 KB
- evals/fixtures/anyof-parameter-variants.yaml 660 B
- evals/fixtures/discriminator-with-allof.yaml 1.1 KB
- evals/fixtures/regex-pattern-field.yaml 764 B
- references/drift-mapping.md 13 KB
- references/example-repos.md 1.8 KB
- references/schema-patterns.md 11 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.
- 2d ago First seen · 140 lines · 145 tokens per session scan A 85d80b339744
openapi-parser is a skill published in the GitHub repository pactflow/pactflow-agent-skills (6 stars, last pushed 9d ago), licensed MIT. It adds 145 tokens to every session and 1,419 once invoked, about $0.0007 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
codex-docs-drift-scout
Install the AutoHub docs-drift Codex automation from signed AutoVault skill resources and audit its render fidelity with autovault doctor.
Agent Instruction Drift Check
Procedure for comparing an agent-facing instruction doc (AGENTS.md/CLAUDE.md-style) against the actual current code and configuration to find and flag mismatches.
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…