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/davidteren/intent-engineering/ie-validate-plannpx skills add davidteren/intent-engineering --skill ie-validate-plangit clone --depth 1 https://github.com/davidteren/intent-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/davidteren/intent-engineering/ie-validate-plan)<a href="https://agentmods.dev/skills/davidteren/intent-engineering/ie-validate-plan"><img src="https://agentmods.dev/badge/skills/davidteren/intent-engineering/ie-validate-plan.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 | $0.00079 | $0.01541 |
| Opus 5 | $0.00039 | $0.00771 |
| Sonnet 5 | $0.00016 | $0.00308 |
| Haiku 4.5 | $0.00008 | $0.00154 |
Grade A, and why
ie-validate-plan 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 5d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent Engineering — Plan Validation
Reviews a document (plan, spec, or requirements) for the design decisions that, if left surprising / non-idiomatic / over-complex / UX-incomplete, will derail implementation. Catches the problem at the cheapest point — before code exists. Fans out the four lenses in plan mode, each rating its dimensions 0-10 and naming the gaps.
Argument parsing
| Token | Effect |
|---|---|
mode:agent |
Emit JSON; no interactive routing. |
out:<path> |
Override published report path (file or dir). Defaults: scratch .intense/runs/<run-id>/, publish docs/intent-engineering/<stamp>-validate-plan[-scope].md. |
config:<path> |
Override project config directory (walk-up / INTENSE_CONFIG_DIR otherwise). |
| remainder | Path to the document. If omitted, find the most recent under docs/plans/, docs/brainstorms/; if none, ask once which file. |
Stage 1 — Read & classify
Read the document. Classify by content shape, not path (path is a tie-breaker):
requirements(what-to-build): actors, flows, acceptance examples, R/A/F IDs, user/business framing, no implementation units. A requirements doc may legitimately defer interaction mechanics to planning.plan(how-to-build): implementation units (U1, U2), per-unit files/approach/ tests, technical decisions, sequencing. A plan that commits to building UI must enumerate the states.
Pass Document type: to every lens — it changes how strict each lens is (a
requirements doc is allowed to defer detail a plan must pin down).
Stage 2 — Select lenses
First load resolved config per ${CLAUDE_PLUGIN_ROOT}/references/config-resolution.md
(walk-up / config: / INTENSE_CONFIG_DIR, then merge over config/defaults/) — the
lenses: toggles, conventions, and confidence_gate apply here too. Always state
Config source in Coverage. (The architecture lens is code-only and does not run in plan
validation.) Then read ${CLAUDE_PLUGIN_ROOT}/references/lens-catalog.md.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 121 lines · 79 tokens per session scan A f2158032bb85
ie-validate-plan is a skill published in the GitHub repository davidteren/intent-engineering (3 stars, last pushed 20d ago), licensed MIT. It adds 79 tokens to every session and 1,541 once invoked, about $0.0004 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
refactoring-the-assembled-ui
Edit, split or share the CSS and JavaScript under plugins/audit/scripts/ui/ — files Python concatenates into one inline and one inline carrying code, in a self-contained page opened over file://. Covers the assembly contract and the byte-level pins in plugins/audit/tests/ that guard it, why the split must be an…
choosing-what-to-optimize
Decide what is worth making faster in this repo, and prove it paid — measure the thing instead of grepping for it, separate wall clock from total CPU from the critical path, rank targets by shape rather than by how many modules import them, and decline the work with a number when the number says so. Use this whenever…
running-resumable-sync-jobs
Design and review long-running batch or sync jobs that process many items against a remote API and persist checkpoint state — exit codes that report partial failure, checkpoints that are safe to resume, per-item tolerance vs. fatal abort, telling "zero" apart from "couldn't fetch", bounded retries, and honest…
verifying-external-behavior
Confirms what a third-party library, remote API, build backend, or scraped document actually does before writing code that depends on it — throwaway probes that run in seconds, permissive clients that forward wrong arguments instead of rejecting them, per-endpoint docs that don't generalize, response shapes that make…
writing-javascript
How browser JavaScript is written in this repo — both surfaces now speak one modern dialect and this says what that means for the code you type, where ES modules are impossible and where they are merely unused, and how to pick a feature (Baseline plus a file:// gate). Covers functional idiom over imperative DOM work…
journey-simulation
Use when caller wants to observe how a stranger encounters a flow, artifact, or sandbox — triggers like "simulate a user journey", "test our onboarding / checkout / signup", "will my ICP convert", "how does a cold reader experience this README", "first-time user test", "cognitive walkthrough", or any request to…