Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add davidteren/intent-engineering/plugin install 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-plan-assist)<a href="https://agentmods.dev/skills/davidteren/intent-engineering/ie-plan-assist"><img src="https://agentmods.dev/badge/skills/davidteren/intent-engineering/ie-plan-assist.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 | $0.00079 | $0.01140 |
| Opus 5 | $0.00039 | $0.00570 |
| Sonnet 5 | $0.00016 | $0.00228 |
| Haiku 4.5 | $0.00008 | $0.00114 |
Grade A, and why
ie-plan-assist 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent Engineering — Planning Assist
A fast, advisory pass that brings the principles to the table while you plan, so the design starts intuitive instead of being corrected later. It does not fan out a heavy review or score anything — it emits a tailored checklist of the considerations that matter for this work, drawn from the principle docs.
When to use
- Drafting an approach or a plan, before a finished plan doc exists.
- Deciding between designs and wanting the principle trade-offs surfaced.
- As a planning-phase companion (a planning workflow can call this to enrich a draft).
For a finished plan/spec doc, use ie-validate-plan. For code, use ie-review.
How it works
This skill runs inline (no sub-agents by default — it's meant to be quick and conversational). Steps:
-
Establish the subject. Use the argument, or the current plan draft / conversation, to state in one line what's being planned and identify the surface(s): backend logic, public API/interface, framework/stack, user-facing UI, data/config.
-
Select the relevant principles. Read only the docs that apply (from
${CLAUDE_PLUGIN_ROOT}/resources/— seereferences/principle-index.md):- Always:
principles/least-astonishment.md,principles/occams-razor.md. - API/interface or naming decisions:
agnostic/api-design.md,agnostic/naming.md,agnostic/error-handling.md,principles/dwim.md. - Framework/stack chosen: the matching
frameworks/<stack>.md+principles/convention-over-configuration.md+agnostic/defaults-and-configuration.md. - User-facing surface:
principles/human-interface-guidelines.md,principles/ux-design.md,principles/look-and-feel.md,agnostic/accessibility.md,agnostic/information-architecture.md.
- Always:
-
Emit a tailored checklist, grouped by lens, of the concrete decisions to get right up front. Each item is a question or guard specific to the subject — not a generic principle restatement. Examples:
- Predictability: "Name the new endpoint after what it does — will
GET /accounts/:id/summaryever mutate? If caching, make the write explicit." - Convention: "This is Rails — model the cancellation as a RESTful sub-resource
(
DELETE/nested resource), not a customcancelaction, unless the repo already does custom actions." - Simplicity: "You're adding a strategy interface for one payment provider — defer it until the second provider is real (YAGNI)."
- Experience: "List the states for the new filter: loading, empty, error, no-match — and the keyboard path. Decide them now, not in code review."
- Predictability: "Name the new endpoint after what it does — will
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.
- 8d ago First seen · 89 lines · 79 tokens per session scan A f9f49e25ca1b
ie-plan-assist is a skill published in the GitHub repository davidteren/intent-engineering (3 stars, last pushed 23d ago), licensed MIT. It adds 79 tokens to every session and 1,140 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…
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…
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…
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…
reproducing-ci-locally
Run the CI gate on your machine so it agrees with the runner — deriving the exact command, paths, markers, and env from the workflow file instead of the Makefile, unblocking gate steps that short-circuit and hide the next failure, pinning the linter version CI resolves, and confirming the run is green instead of…