coral-review-source-spec

coral-review-source-spec is a skill for Codex from withcoral/coral. It costs 75 tokens per session (2,122 once invoked), scanned A, original, Apache-2.0.

A review guide for Coral source definitions, which describe where Coral gets information and how users or agents can search it. It covers source files, manifests, documentation, and pull requests.

In plain words
What is it for?
Reviewing Coral source directories, manifest.yaml files, related documentation, tests, and pull requests that add or update sources.
Why use it?
It helps reviewers judge whether a new source is understandable, useful, safe, and consistent, beyond checking whether its files are valid.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions AGENTS.md; mentions Codex.

Good fit Reviewing Coral source directories, manifest.yaml files, related documentation, tests, and pull requests that add or update sources.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/withcoral/coral/coral-review-source-spec
About the project

Coral is a local application that gives AI agents one SQL interface for querying connected APIs, files, and live data sources. It is for agents and developers who need to retrieve and correlate data across sources while reducing repeated tool calls, pagination, and source-specific integration code. Coral exposes its query interface to compatible agents through MCP, and the catalogue add-ons support using it in agent workflows.

withcoral/coral · 4,953 stars · on GitHub · withcoral.com

Install

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.

Any agent
npx skills add withcoral/coral --skill coral-review-source-spec
Clone the repo
git clone --depth 1 https://github.com/withcoral/coral

Made for: Codex.

Wrote 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.

agentmods badge for coral-review-source-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/withcoral/coral/coral-review-source-spec/github.svg)](https://agentmods.dev/skills/withcoral/coral/coral-review-source-spec)
Your own site
<a href="https://agentmods.dev/skills/withcoral/coral/coral-review-source-spec"><img src="https://agentmods.dev/badge/skills/withcoral/coral/coral-review-source-spec/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.

agentmods 80×15 button for coral-review-source-spec

Your own site · 80×15
<a href="https://agentmods.dev/skills/withcoral/coral/coral-review-source-spec"><img src="https://agentmods.dev/badge/skills/withcoral/coral/coral-review-source-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,122 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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 Privilege Escalation · line 46
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00075 $0.02122
Opus 5 $0.00037 $0.01061
Sonnet 5 $0.00015 $0.00424
Haiku 4.5 $0.00007 $0.00212

Measured 4d ago against content hash f98d0a2314ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

coral-review-source-spec 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.

plugins/coral/skills/coral-review-source-spec/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coral Review Source Spec

Review Goal

Review the source as product surface. Do not spend the review mainly restating CI, schema validation, or YAML lint results unless those failures are visible and relevant. Focus on whether the source will be understandable, useful, safe, and consistent for Coral users and agents.

Workflow

  1. Identify the target source directory or PR changes.
    • For a path request, inspect manifest.yaml, any README, and related source docs or tests.
    • For a PR request, find changed files under sources/core/ or sources/community/. If the PR does not add or update a source, say the skill is not applicable and review normally.
  2. Read guidance in the Coral repo before judging style:
    • CONTRIBUTING.md, especially "Source contributions".
    • The repo AGENTS.md and any nearer AGENTS.md.
    • Similar existing sources in sources/core/ and the community example in sources/community/hn/.
  3. Compare against existing source patterns, not a generic API-wrapper ideal. Look at nearby sources with similar shape: public no-auth APIs, token APIs, OAuth-backed APIs, GraphQL APIs, search-heavy APIs, log/time-series APIs, or generated large API sources.
  4. Produce a code-review style result: findings first, ordered by severity, with file and line references. Include open questions only after findings. If there are no substantive issues, say so and mention residual risks or review gaps.

Review Checklist

These checks should be based on the authoritative API docs for the API the source exposes.

Scope and Fit

  • Source belongs in the right tree: sources/community/ for community sources; new sources/core/ additions need prior discussion per CONTRIBUTING.md. PRs from external contributors should almost always be in sources/community.
  • If reviewing a new source, ensure it doesn't replicate the functionality of an existing source.
  • Source name is clear, stable, lowercase, and matches the SQL schema users will type.
  • Scope is narrow enough to be coherent. A small source should expose the main user workflows, not every marginal endpoint.
  • No real credentials, customer data, internal fixtures, or private URLs are committed.
  • Updated sources bump version when user-visible behavior, tables, columns, inputs, or semantics change.

Read the full file on GitHub · 109 lines

Files

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.

Changes

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.

  1. 4d ago Changed f98d0a2314ea
  2. 13d ago First seen · 109 lines · 75 tokens per session scan A 53bfb66f31cc

Subscribe to this mod's changes

coral-review-source-spec is a skill published in the GitHub repository withcoral/coral (4,953 stars, last pushed yesterday), licensed Apache-2.0. It adds 75 tokens to every session and 2,122 once invoked, about $0.0004 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.