A tool-assisted method for investigating agent problems by inspecting runtime state, event history, token use, and available tools.

Use it when a tool call behaves unexpectedly, the agent gets stuck, debugging features seem unavailable, or you need to inspect the session itself.

It helps explain unexpected failures, repeated actions, missing features, or suspected context limits.

How matteing/opal configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to matteing/opal. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/matteing/opal/main/.claude/skills/citations/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/matteing/opal

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/matteing/opal/citations/github.svg)](https://agentmods.dev/skills/matteing/opal/citations)

Your own site

<a href="https://agentmods.dev/skills/matteing/opal/citations"><img src="https://agentmods.dev/badge/skills/matteing/opal/citations/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/matteing/opal/citations"><img src="https://agentmods.dev/badge/skills/matteing/opal/citations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 220 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00042	$0.00220
Opus 5.5	$0.00017	$0.00088
Sonnet 5.5	$0.00008	$0.00044
Haiku 4.5	$0.00004	$0.00022

Measured 2mo ago against content hash b1b1603798b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

citations 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.

.claude/skills/citations/SKILL.md · 18 lines

What it actually says

Citations Skill

When the user provides a link or citation, add it to docs/research/references.md automatically.

Rules

Categorize — place the reference under the most appropriate existing ## section. Create a new section only if nothing fits.
Format — use the existing bullet style: - [Title](URL) — One-sentence description. (source-context)
Deduplicate — if the URL already exists in the file, update the description instead of adding a duplicate.
TODO section — if the reference is speculative or needs further review, place it under the ## TODO section at the bottom instead.
No prompting — do not ask the user whether to add the reference. Just add it.

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.

2mo ago First seen · 18 lines · 42 tokens per session scan A b1b1603798b6

Subscribe to this mod's changes

citations is a skill published in the GitHub repository matteing/opal (62 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 220 once invoked, about $0.0002 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 2026-08-30.

LLM Research Writing and docs agents ai ai-agents cli elixir

citations next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
citationsmatteing/opal	Skill	62	2mo ago	MIT	A	42	Claude Code
building-agentsericrisco/rsc-harness	Skill	503	2d ago	MIT	A	85	Claude Code, Codex
agent-evalericrisco/rsc-harness	Skill	503	2d ago	MIT	A	79	Claude Code, Codex
code-reviewdamianvtran/local-operator	Skill	229	yesterday	MIT	A	45	Claude Code, Codex
browser-qadamianvtran/local-operator	Skill	229	yesterday	MIT	A	45	Claude Code, Codex
design-qadamianvtran/local-operator	Skill	229	yesterday	MIT	A	50	Claude Code, Codex
engineering-principlesdamianvtran/local-operator	Skill	229	yesterday	MIT	A	42	Claude Code, Codex

opal: Skill for Claude Code