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.
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 withcoral/coral --skill coral-review-source-specgit clone --depth 1 https://github.com/withcoral/coralWrote 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/withcoral/coral/coral-review-source-spec)<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.
<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>- NVIDIA SkillSpector warn
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.
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 | $0.00075 | $0.02122 |
| Opus 5 | $0.00037 | $0.01061 |
| Sonnet 5 | $0.00015 | $0.00424 |
| Haiku 4.5 | $0.00007 | $0.00212 |
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.
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
- 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/orsources/community/. If the PR does not add or update a source, say the skill is not applicable and review normally.
- For a path request, inspect
- Read guidance in the Coral repo before judging style:
CONTRIBUTING.md, especially "Source contributions".- The repo
AGENTS.mdand any nearerAGENTS.md. - Similar existing sources in
sources/core/and the community example insources/community/hn/.
- 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.
- 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; newsources/core/additions need prior discussion perCONTRIBUTING.md. PRs from external contributors should almost always be insources/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
versionwhen user-visible behavior, tables, columns, inputs, or semantics change.
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 Changed f98d0a2314ea
- 13d ago First seen · 109 lines · 75 tokens per session scan A 53bfb66f31cc
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…