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 angad-kandhari/deliberate --skill reviewgit clone --depth 1 https://github.com/angad-kandhari/deliberateWrote 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/angad-kandhari/deliberate/review)<a href="https://agentmods.dev/skills/angad-kandhari/deliberate/review"><img src="https://agentmods.dev/badge/skills/angad-kandhari/deliberate/review/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/angad-kandhari/deliberate/review"><img src="https://agentmods.dev/badge/skills/angad-kandhari/deliberate/review.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00057 | $0.01454 |
| Opus 5 | $0.00028 | $0.00727 |
| Sonnet 5 | $0.00011 | $0.00291 |
| Haiku 4.5 | $0.00006 | $0.00145 |
Grade A, and why
review 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 10d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review
Code review skill for LLM coding agents. Load this when reviewing a PR, reviewing your own diff before handing it back, or auditing code someone else wrote.
Where deliberate keeps writing honest, this skill keeps reviewing honest. Counters rubber-stamp "LGTM" reviews, nitpick-only reviews, and missing the forest for the trees.
1. Read the Intent First, Code Second
Know what the change is trying to do before judging how it does it.
- Read the PR description, linked ticket, or commit message before the diff.
- If you can't state the goal in one sentence, ask - don't review blind.
- A clean implementation of the wrong thing is worse than a messy implementation of the right thing.
If intent is missing:
"I can review the code, but I need the goal first. What problem is this solving?"
Test: Can I say in one sentence what this change is for?
2. Review in Layers, Top-Down
Don't start with nits. Start with correctness.
Review in this order, and stop at the first layer that has a blocking issue:
- Does it solve the stated problem? If not, nothing else matters.
- Is the approach sound? Right abstraction, right layer, right trade-offs.
- Is it correct? Edge cases, error paths, concurrency, data integrity.
- Is it safe? Auth, input validation, injection, secrets, PII.
- Is it maintainable? Naming, structure, testability.
- Is it consistent? Matches surrounding code style and conventions.
- Nits. Formatting, spelling, preferences.
Leaving an architectural concern to the end while drowning the author in nits is a failure mode. Start at the top.
Test: Are my highest-priority comments about the highest-priority concerns?
3. Distinguish Blocking From Non-Blocking
Label every comment so the author knows what to act on.
Use clear prefixes:
blocking:must be addressed before merge.question:genuine ask, not a veiled critique.suggestion:take it or leave it.nit:cosmetic, optional.praise:noting what's good. Worth doing.
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.
- 10d ago First seen · 165 lines · 57 tokens per session scan A 57afb8d85c41
review is a skill published in the GitHub repository angad-kandhari/deliberate (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,454 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 2026-08-31.
Other skills, from other repositories
procoder
Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…
explain
Guided code tour of a file or subsystem this session touched — entry point, the load-bearing pieces, the edges, and what connects to it.
x-spec
A system-planning guide that turns a vague idea into a set of linked design documents. It defines goals, modules, interfaces, data, workflows, and ways to check the result.
x-audit-arch
A project-wide architecture review skill that checks whether code is placed in the right modules and whether important definitions have one reliable source.
x-multi-llm-align
A review process in which two sub-agents examine an API, data format, event schema, or workflow from their separate implementation perspectives. The user passes documents and feedback between them over multiple rounds.
x-cr
A software-correctness investigation skill for finding why code behaves differently from what was expected. It uses evidence from code paths, specifications, tests, logs, and changes to assess possible causes.