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/stchiotis/library-first-engineering/lfe-plan-critiquenpx skills add StChiotis/Library-First-Engineering --skill lfe-plan-critiquegit clone --depth 1 https://github.com/StChiotis/Library-First-EngineeringWrote 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/stchiotis/library-first-engineering/lfe-plan-critique)<a href="https://agentmods.dev/skills/stchiotis/library-first-engineering/lfe-plan-critique"><img src="https://agentmods.dev/badge/skills/stchiotis/library-first-engineering/lfe-plan-critique.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 | $0.00056 | $0.03207 |
| Opus 5 | $0.00028 | $0.01604 |
| Sonnet 5 | $0.00011 | $0.00641 |
| Haiku 4.5 | $0.00006 | $0.00321 |
Grade A, and why
lfe-plan-critique 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 6d 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.
LFE Plan Critique — Pre-Build 5-Lens Review
Position in Pipeline
- Phase: 1.5 (between Architect plan approval and Builder start)
- Persona: Architect (read-only — no src/ write access)
- Trigger: Automatically after Brain approves
active_plan.md— before/lfe-builderis invoked - Next Step:
/lfe-builder(on PASS) or/lfe-architectrevision loop (on BLOCK)
Mission
Stress-test the approved plan from five angles before a single line of code is written. Catch ambiguous acceptance criteria, untestable requirements, domain boundary violations, structural impact, and cross-edit incoherence before they become bugs in src/. The five lenses are judgment calls; a mechanical pre-pass (Step 1.5) first surfaces the objective, checkable defects into Lens 2 (glob reach, line-count and existence-check antipatterns) and Lens 5 (orphan-word candidates), so the judgment lenses reason over verified facts rather than guesses.
Hard Rules
- Zero Code Writes: This skill operates on
.plans/and.docs/only —src/stays untouched. - 5-Lens Sequential: Run all five lenses in order, every time — even when an earlier lens passed cleanly. Run the mechanical pre-pass (Step 1.5) first, so Lens 2 and Lens 5 reason over its findings.
- Single Output File: All findings aggregate into one
plan_critique.md— no per-lens files. - Verdict is Decisive: A single BLOCK finding stops the Builder. WARN requires an explicit, file-recorded Brain confirmation before Builder starts (see Step 7 —
brain_confirmationfrontmatter field). - Domain Library Is Truth: All domain boundary and architectural judgments must cite a specific
.docs/file and line, not general knowledge. - Revision Counter (file-based): The
revision:field inplan_critique.mdfrontmatter is the physical substrate for the 2-revision limit (GOVERNANCE Cycle Limits). On every run, read any existingplan_critique.mdfirst to determine the current revision number. On a 2nd BLOCK, halt and present Brain triage instead of looping back. This rule exists because the file is overwritten each run — without the counter, the limit would be conversation-only and lost on crash.
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.
- 6d ago First seen · 165 lines · 56 tokens per session scan A 2a69552c2f2f
lfe-plan-critique is a skill published in the GitHub repository StChiotis/Library-First-Engineering (43 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 3,207 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 2026-08-30.
Other skills, from other repositories
playwright
Use when the task requires capturing or automating a real browser from the terminal.
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
implementation-final-review
Perform the repository's risk-tiered independent final review before implementation completion. Use only when explicitly invoked or when repository instructions require it after behavior-impacting implementation work; audit the complete task diff, supported contracts, lifecycle and security boundaries, complexity, and…
promptfoo-provider-setup
Configure promptfoo providers or redteam targets for hosted models, live HTTP APIs, Python/JavaScript local scripts, agent SDKs, or multi-input systems. Use when connecting promptfoo to the system under test, mapping vars, auth env vars, request bodies, response transforms, or static-code-derived provider wrappers. Do…
redteam-plugin-development
Standards for creating redteam plugins and graders. Use when creating new plugins, writing graders, or modifying attack templates.
search-params
URL search param and hash state management. Use when adding or modifying URL search params, working with useSearchParams, setSearchParams, useSearchParamState, or navigate() with query strings or hash fragments, or fixing browser back/forward button issues.