source-reviewer

A review tool that reads public source notes and creates a limited summary with unanswered questions. It only describes this review workflow and does not install or run other resources.

In plain words
What is it for?
Use it to summarize public notes and identify questions that still need answers.
Why use it?
It turns supplied notes into a short review without executing code, changing settings, or relying on trusted lifecycle actions.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/rookiestar28/agentique-cli/codex-skill
Any agent
npx skills add rookiestar28/Agentique-CLI --skill codex-skill
Clone the repo
git clone --depth 1 https://github.com/rookiestar28/Agentique-CLI

Made for: Claude Code, Codex.

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 119 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00014 $0.00119
Opus 5 $0.00007 $0.00060
Sonnet 5 $0.00003 $0.00024
Haiku 4.5 $0.00001 $0.00012

Measured 3d ago against content hash f60d0338c2e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

source-reviewer 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 3d 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.

starters/portable-profile-review/codex-skill/SKILL.md · 25 lines

What it actually says

Source Reviewer

This is a descriptor-only generated adapter. It does not install or execute resources.

Boundary:

  • descriptor-only
  • do not install or execute
  • no lifecycle hooks are trusted
  • no user agent configuration is written
  • target: codex-skill

Command: summarize-public-source

Profile: review Mode: summarize Aliases: summarize

Summarizes public source notes with no execution.

Read the provided public notes and produce a concise summary with open questions.

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. 3d ago First seen · 25 lines · 14 tokens per session scan A f60d0338c2e5

Subscribe to this mod's changes

source-reviewer is a skill published in the GitHub repository rookiestar28/Agentique-CLI (14 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 119 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

author

Scaffold a conforming AI-layer artifact — a rule, skill, hook, agent, or output style — that already passes the format checks, then verify it. Use when adding any new .claude/ artifact, so it matches the existing shape instead of drifting.

Ashkaan/contextium · 56 tokens

close

The "wrap" verb of the loop — end the session by writing the journal entry, updating touched project READMEs, committing, and pushing. Auto-invoked as the tail of /spec and /implement (the producer verbs) on clean completion, so "wrap" is not a verb the user types; also runnable directly. Dispatches /implement-audit…

Ashkaan/contextium · 121 tokens

debate

Adversarial debate — spawn competing AI agents to argue a question, then synthesize the strongest conclusion. Use when the user says "debate this", "I'm torn between X and Y", "red-team this plan", or "council on this".

Ashkaan/contextium · 56 tokens

explain

Deep research into a topic or issue — investigate until confident, then present executive summary and root cause analysis. Use when you need to understand WHY.

Ashkaan/contextium · 32 tokens

spec-audit

Adversarial review of a freshly-written or materially-rewritten SPEC, before any code is written. Runs an independent reviewer against the SPEC's design and the spirit-check agent against the user's verbatim ask, in one pass. Auto-fired by /spec; also callable standalone after any SPEC edit. Emits the spec-audit…

Ashkaan/contextium · 77 tokens

implement-audit

Adversarial review of freshly-built code — find what was missed, what's inconsistent, what breaks. The single code reviewer for the loop, and it runs exactly once per session. Auto-fired by /implement; standalone-callable after any substantial ad-hoc change. Emits the implement-audit: commit trailer the git hook…

Ashkaan/contextium · 71 tokens