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.
git clone --depth 1 https://github.com/alberduris/skillsWrote 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/commands/alberduris/skills/plan-review)<a href="https://agentmods.dev/commands/alberduris/skills/plan-review"><img src="https://agentmods.dev/badge/commands/alberduris/skills/plan-review.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 5.1 | $0.00021 | $0.00395 |
| Opus 5 | $0.00010 | $0.00198 |
| Sonnet 5 | $0.00004 | $0.00079 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
plan-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 8d 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.
What it actually says
Load the newspaper-explainer skill. Read ./templates/broadsheet.html and ./references/css-patterns.md to absorb the canonical structure, CSS class vocabulary, and palette. Then generate a broadsheet newspaper edition reviewing a plan document against the actual codebase.
The plan file is $1 (path to a markdown plan, spec, or RFC). The codebase is $2 if provided, otherwise the current working directory. Gather ALL facts before writing HTML: a) read the plan in full and extract every proposed change, assumption, and scope boundary, b) read every file the plan references AND files that import or depend on those files, c) map the blast radius — what callers, tests, configs, and public API surface are affected, d) cross-reference plan vs code — does every file, function, and type the plan mentions actually exist and behave as described.
The LEAD STORY presents the plan's core thesis and the assessment verdict (viable, risky, incomplete, etc.). The floating INSET BOX carries impact metrics (files to modify, files to create, estimated scope, test coverage). SECONDARY STORIES cover individual areas of change as separate articles, each with a side-by-side current-vs-planned comparison. The SIDEBAR reports completeness indicators (does the plan cover tests, docs, migration, rollback). LETTERS AND CORRESPONDENCE reconstructs rationale gaps — changes where the plan says WHAT but not WHY, presented as unanswered questions to the plan author. The DISPATCH BOARD surfaces risks: edge cases not addressed, assumptions that need verification, ordering dependencies, cognitive complexity hotspots with concrete mitigation suggestions.
NEVER EVER fabricate facts — every claim must be traceable to the plan document or actual file contents. Write to ~/.agent/newspapers/ and open in the browser.
Ultrathink.
$@
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.
- 8d ago First seen · 15 lines · 21 tokens per session scan A a7f46f7c28ec
plan-review is a command published in the GitHub repository alberduris/skills (18 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 395 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.