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/intelligencedev/manifold/manifold-apinpx skills add intelligencedev/manifold --skill manifold-apigit clone --depth 1 https://github.com/intelligencedev/manifoldWrote 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/intelligencedev/manifold/manifold-api)<a href="https://agentmods.dev/skills/intelligencedev/manifold/manifold-api"><img src="https://agentmods.dev/badge/skills/intelligencedev/manifold/manifold-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 | $0.00035 | $0.00409 |
| Opus 5 | $0.00017 | $0.00204 |
| Sonnet 5 | $0.00007 | $0.00082 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
manifold-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.
- **Dependencies**: `curl`, `jq` What it actually says
Manifold API Skill
Purpose
The Manifold API skill is designed to interact safely with the local Manifold HTTP API running at http:/localhost:32180. It provides helper scripts to inspect the OpenAPI spec (/openapi.json) safely without dumping large documents into context, and rules for avoiding destructive operations and redacting sensitive information.
Usage
Use the provided shell script to interact with the Manifold API spec or health endpoints safely:
# Check if the API is running
./manifold-api/main.sh healthz
# Get the OpenAPI definition for a specific path (e.g., /api/projects)
./manifold-api/main.sh spec-path "/api/projects"
Configuration
- Dependencies:
curl,jq - Target URL: Defaults to
http:/localhost:32180
File Structure
manifold-api/SKILL.md: This documentation template and skill rules.manifold-api/main.sh: Entry point script for interacting with the API safely.
Best Practices & Rules
- Filter Specs: Never dump the full
openapi.jsoninto context. Use themain.sh spec-pathscript to inspect one path at a time. - Redaction: Redact
apiKey, bearer tokens, cookies, auth headers, andextraHeadersvalues in API responses. - Safety First: Always ask before modifying
/api/config/agentdor deleting objects like specialists, teams, sessions, workflows, datasets, experiments, or prompt versions. - Data Shapes: Use live
GETrequests to discover the structure ofGenericObjectfields before sendingPOST/PUT/PATCHrequests. Do not invent request fields.
What ships with it
1 file 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 · 40 lines · 35 tokens per session scan A 39d57cbda2c8
manifold-api is a skill published in the GitHub repository intelligencedev/manifold (497 stars, last pushed 26d ago), licensed MIT. It adds 35 tokens to every session and 409 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
release-notes
Draft concise release notes.
ship-and-babysit
End-to-end PR shipping workflow for tinyhumansai/openhuman: commit local changes, push to the user's fork, open or reuse a PR against main, then babysit CI and CodeRabbit feedback until the PR is green and clean. Use when the user asks to ship, open a PR, monitor CI, address review comments, or 'babysit' a branch.
adr-skill
Create and maintain Architecture Decision Records (ADRs) optimized for agentic coding workflows. Use when you need to propose, write, update, accept/reject, deprecate, or supersede an ADR; bootstrap an adr folder and index; consult existing ADRs before implementing changes; or enforce ADR conventions. This skill uses…
add-harness-package
Guide for adding new AI SDK harness packages. Use when creating a new @ai-sdk/harness- package that adapts a coding-agent runtime to HarnessV1.
add-provider-package
Guide for adding first-party AI provider packages to the AI SDK. Use when creating a provider package under packages/ to integrate an external AI service.
update-provider-models
Add new or remove obsolete model IDs for existing AI SDK providers. Use when adding a model to a provider, removing an obsolete model, or processing a list of model changes from an issue. Triggers on "add model", "remove model", "new model ID", "obsolete model", "update model IDs".