pchalasani/claude-code-tools is a collection of command-line tools, skills, agents, hooks, plugins, and commands for improving work with Claude Code, Codex-CLI, and similar coding agents. It is used by developers who want reusable productivity features and workflows for terminal-based AI coding assistants. The catalogue entries are components of, or extensions for, these coding-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 agentmods add skills/pchalasani/claude-code-tools/visual-briefnpx skills add pchalasani/claude-code-tools --skill visual-briefgit clone --depth 1 https://github.com/pchalasani/claude-code-toolsWrote 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/pchalasani/claude-code-tools/visual-brief)<a href="https://agentmods.dev/skills/pchalasani/claude-code-tools/visual-brief"><img src="https://agentmods.dev/badge/skills/pchalasani/claude-code-tools/visual-brief.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 | $0.00058 | $0.01746 |
| Opus 5 | $0.00029 | $0.00873 |
| Sonnet 5 | $0.00012 | $0.00349 |
| Haiku 4.5 | $0.00006 | $0.00175 |
Grade A, and why
visual-brief 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 today.
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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Brief
Start with a Visible Acknowledgment
Before a long setup or implementation block, send the human a short visible acknowledgment in the current conversation. Say what you are starting and where you will publish the result. Do this before creating files or running lengthy commands.
The same rule applies to a substantial request sent through the page. Answer the thread first with one short confirmation. Publish the completed work later. If the request takes only a moment, answer it directly without a separate acknowledgment.
Use the Page as the Report
The human reads the page. The chat only points to it. Put the complete report on the page, including conclusions, limits, reasoning, and evidence. Do not repeat the report in the terminal response.
A visual brief is useful for substantial implementation results, design reports, investigations, reviews, and decision sets. Trivial progress and small fixes belong in ordinary conversation. An explicit request for a visual brief overrides this threshold.
The page supports layers:
glancestates one plain claim.explanationgives the reasoning in full.forensicsholds raw evidence, file paths, output, errors, and numbers.tableshold repeated or comparable values.
Keep each prose field as a flowing thought. Several distinct facts should be
separate items, table rows, or forensic notes. Do not cram numbered lists into
glance, explanation, or a conversation turn.
Publish One Complete Briefing
Every normal publish accepts one JSON object with exactly these fields:
idtimestampheadlinesummarylanes
visual-brief publish appends that object to updates. The last entry,
updates[-1], is the latest briefing. The page gives it the prominent card
treatment. When another briefing arrives, the prior latest keeps its stable id
and moves into the quieter earlier-briefing ledger. Its folds, drafts,
conversations, and pending state remain attached to the same record.
What ships with it
60 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.
- example.json 12 KB
- frontend/index.html 2.5 KB
- frontend/inline-safety.test.ts 1.5 KB runs code
- frontend/inline-safety.ts 3.2 KB runs code
- frontend/package-lock.json 88 KB
- frontend/package.json 630 B
- frontend/src/age.ts 2.7 KB runs code
- frontend/src/app.tsx 10 KB
- frontend/src/compose-view.tsx 6.2 KB
- frontend/src/composer.test.ts 14 KB runs code
- frontend/src/composer.ts 10.0 KB runs code
- frontend/src/current-state.test.tsx 21 KB
- frontend/src/current-state.tsx 5.0 KB
- frontend/src/cursor.test.ts 2.1 KB runs code
- frontend/src/cursor.ts 2.5 KB runs code
- frontend/src/design-toggle.test.tsx 4.7 KB
- frontend/src/design-variant.test.ts 4.8 KB runs code
- frontend/src/design-variant.ts 8.0 KB runs code
- frontend/src/document-feed.test.ts 7.9 KB runs code
- frontend/src/document-feed.ts 5.7 KB runs code
- frontend/src/document.test.ts 6.2 KB runs code
- frontend/src/document.ts 8.1 KB runs code
- frontend/src/evidence-view.tsx 2.7 KB
- frontend/src/evidence.ts 3.7 KB runs code
- frontend/src/global-message.test.tsx 11 KB
- frontend/src/hints.test.ts 7.4 KB runs code
- frontend/src/hints.ts 3.4 KB runs code
- frontend/src/human-state.test.ts 5.3 KB runs code
- frontend/src/human-state.ts 6.7 KB runs code
- frontend/src/item-view-click.test.tsx 8.7 KB
- frontend/src/item-view.tsx 3.6 KB
- frontend/src/keys.test.ts 7.8 KB runs code
- frontend/src/keys.ts 3.7 KB runs code
- frontend/src/lane-chat.test.tsx 4.9 KB
- frontend/src/live-document.ts 4.9 KB runs code
- frontend/src/live-publish.test.tsx 8.9 KB
- frontend/src/live-rows.ts 2.0 KB runs code
- frontend/src/main.tsx 2.0 KB
- frontend/src/markdown-blocks.ts 5.5 KB runs code
- frontend/src/markdown-in-page.test.tsx 3.8 KB
- frontend/src/markdown-view.tsx 2.8 KB
- frontend/src/markdown.test.tsx 9.1 KB
- frontend/src/markdown.ts 8.3 KB runs code
- frontend/src/navigation.ts 10 KB runs code
- frontend/src/open.test.ts 6.9 KB runs code
- frontend/src/open.ts 3.3 KB runs code
- frontend/src/outline.ts 5.2 KB runs code
- frontend/src/overlays.tsx 3.9 KB
- frontend/src/page-meta.test.ts 2.0 KB runs code
- frontend/src/page-meta.ts 2.4 KB runs code
- frontend/src/pending.test.ts 16 KB runs code
- frontend/src/pending.ts 9.3 KB runs code
- frontend/src/pointer.ts 1.2 KB runs code
- frontend/src/poll-cycle.test.ts 12 KB runs code
- frontend/src/reload.test.ts 2.3 KB runs code
- frontend/src/reload.ts 14 KB runs code
- frontend/src/reveal.ts 1.4 KB runs code
- frontend/src/row-shell.tsx 6.1 KB
- frontend/src/session-store.test.ts 3.8 KB runs code
- frontend/src/session-store.ts 4.9 KB runs code
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.
- today First seen · 220 lines · 58 tokens per session scan A 5fe0c75e6383
visual-brief is a skill published in the GitHub repository pchalasani/claude-code-tools (1,990 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 1,746 once invoked, about $0.0003 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 2026-09-05.
Other skills, from other repositories
rust-expert
Expert Rust programming assistant focused on idiomatic code, safety, and performance.
example
Example skill showing the complete SKILL.md format with all features.
refactor
Code refactoring and optimization.
code-review
Code review and quality analysis.
debug
Problem diagnosis and debugging.
test-writer
Write high-quality unit tests.