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 commands/emtcmca/promptsmith/lensgit clone --depth 1 https://github.com/emtcmca/promptsmithWrote 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/emtcmca/promptsmith/lens)<a href="https://agentmods.dev/commands/emtcmca/promptsmith/lens"><img src="https://agentmods.dev/badge/commands/emtcmca/promptsmith/lens.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 | $0.00043 | $0.02848 |
| Opus 5 | $0.00022 | $0.01424 |
| Sonnet 5 | $0.00009 | $0.00570 |
| Haiku 4.5 | $0.00004 | $0.00285 |
Grade A, and why
lens 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 4d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review an existing artifact and report what's wrong with it. Two modes:
- default (lenses) — critique the artifact through professional lenses; add
--fixto also return a corrected version in one step. --grade— score a prompt against a rubric and return a verdict, not lens findings; add--against <v2>to compare two versions and name what regressed.
Findings tell you what's wrong; --grade tells you how good it is and whether your change
helped. Both run the same engine; the flag picks which.
Step 1 — Load the engine
Read ${CLAUDE_PLUGIN_ROOT}/skills/prompt-engineering/SKILL.md in full. This command runs the LENS path
(engine Step 5 is the core; Steps 2–4 inform what to look for).
Step 2 — Parse arguments
Parse $ARGUMENTS:
--lens <a,b>— explicit lenses. If absent, auto-pick 1–3 by topic (engine Step 5).--fix— after reporting findings, also emit a corrected version of the artifact (Step 6).--grade— grade mode: score the target prompt against a rubric and return a verdict instead of lens findings. Runs the Grade mode section below and skips Steps 3–6.--against <prompt or file>— a second prompt version to compare against. Implies--grade.--rubric <a,b,c>— grade-mode only: grade against these criteria instead of the defaults.- Everything else = the target: a pasted artifact, a description, or a file reference.
Mode gate. If --grade or --against is present, run the Grade mode section (near the
end) and stop — do not run Steps 3–6, and ignore --lens/--fix (a rubric is not a lens). Grade
mode expects a prompt as its target. Otherwise run the default lens flow, Steps 3–6.
If a file path is given, read it — but only within the current project tree; refuse paths that
escape it (.., absolute paths outside cwd) or match secrets (.env, keys, *.pem) and ask the
user to confirm. Never quote secret values into findings. If the target is empty, ask what to
review and stop.
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.
- 4d ago First seen · 183 lines · 43 tokens per session scan A 44f8178610e1
lens is a command published in the GitHub repository emtcmca/promptsmith (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 2,848 once invoked, about $0.0002 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 commands, from other repositories
perf-difficult-conversation
Three-conversations framework rehearsal (Stone/Patton/Heen — Harvard Negotiation Project) for high-stakes conversations — termination, demotion, hard feedback, conflict surfacing. Produces three-conversations breakdown (what-happened / feelings / identity), conversation script with multiple opening choices, SCARF…
culture-onboarding-90
Design a 90-day onboarding architecture for a role. First day (psychological safety + belonging activation), first week (relationship + role context + early wins), first month (skill ramp + integration + baseline), first quarter (autonomous performance + cultural integration check). Written-first elements for…
design-regimen
Design an integrated weekly regimen — training, nutrition, sleep, stress, recovery — matched to the person's actual life. Composes with gym-training-expert and health-nutrition-expert for domain detail. Produces a sustainable architecture, not an extreme program. Not medical advice.
hire-calibrate
Run the pre-loop calibration session — 60 minutes with ≥3 raters, review the rubric, score 2 anchor candidates the team has previously seen, surface inter-rater drift, agree on hire-bar examples. The calibration session itself is the deliverable. Without it, the loop runs on uncalibrated rulers. Per Project Oxygen …
reclaim-knowledge
Organize scattered professional material into a domain-based second-brain architecture. Maps existing sources (Canva, Drive, local folders, Notion, screenshots) to functional domains. Non-technical-friendly — produces folder structure + drag-and-drop instructions, not CLI commands.
build-brand-kit
Produce a complete Brand Kit — positioning, voice rules, color palette, typography stack, visual vocabulary, example applications, don'ts — derived from the person's Genius Profile and Vision Architecture. Composes with frankx-brand, brand-voice, brand-guidelines, theme-factory, infogenius. Integrates with…