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-review)<a href="https://agentmods.dev/skills/davidteren/intent-engineering/ie-review"><img src="https://agentmods.dev/badge/skills/davidteren/intent-engineering/ie-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 | $0.00091 | $0.03269 |
| Opus 5 | $0.00046 | $0.01635 |
| Sonnet 5 | $0.00018 | $0.00654 |
| Haiku 4.5 | $0.00009 | $0.00327 |
Grade A, and why
ie-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.
How it starts
The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent Engineering — Code Review
Reviews a diff for surprise: code that doesn't behave the way a reasonable
developer or user expects, fights convention, adds needless complexity, or skips UX
essentials. Fans out the applicable lenses as parallel sub-agents (the four universal
lenses, plus architecture on a supported framework), merges and confidence-gates their
findings, and writes a report. This is the runtime complement
to the principle docs under ${CLAUDE_PLUGIN_ROOT}/resources/.
Grok users: this skill is the Claude orchestrator. The source repo also has an
optional Grok workflow at .grok/workflows/ie-review.rhai (subset, report in
scratch, no apply). See .grok/workflows/README.md.
Argument parsing
Parse $ARGUMENTS; strip recognized tokens before treating the remainder as a PR
number/URL or branch.
| Token | Effect |
|---|---|
mode:agent |
Report-only; emit JSON (report-template "mode:agent"); skip the apply stage. |
out:<path> |
Override published report path (file or dir). Defaults: scratch .intense/runs/<run-id>/, publish docs/intent-engineering/<stamp>-review[-scope].md. Outside-repo only when explicitly given. |
base:<ref> |
Diff base on the current checkout (skip auto base detection). Do not combine with a PR/branch target. |
plan:<path> |
Plan/spec for context (intent + scope alignment). |
config:<path> |
Override project config directory (see config-resolution). Else walk-up / INTENSE_CONFIG_DIR. |
Operating principles
- Apply locally; never push. In default mode, apply the safe fixes you're
confident in (Stage 5) and commit them as an isolated
fix(ie-review):commit when the tree was clean; on a dirty tree apply but leave for the user. Inmode:agent, mutate nothing — the caller applies. Never push, open PRs, or file tickets. - No blocking prompts. Infer intent and scope from tokens, git state, and the diff. Note uncertainty in Coverage; don't stop to ask.
- Explicit mutations only. Never
git checkout/switchorgh pr checkout. A PR or branch argument selects scope, not permission to switch trees. - Read the repo's standards. Convention findings hinge on local
CLAUDE.md/AGENTS.mdand existing patterns — those override generic ideals.
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 · 224 lines · 91 tokens per session scan A 587d43d7c73a
ie-review is a skill published in the GitHub repository davidteren/intent-engineering (3 stars, last pushed 23d ago), licensed MIT. It adds 91 tokens to every session and 3,269 once invoked, about $0.0005 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
PlanGate 検証監査 (W チェック)
A second review of an existing code review. It compares the review’s findings with the code changes and related planning records to check whether the findings are supported and complete.
rust-intel
Hard rules for writing Rust in code that already compiles and passes tests but is silently broken, slow, or semver-fragile. Load this BEFORE writing any Rust code. Targets bugs that survive rustc, clippy, and cargo test but fail in production or rot the codebase. Covers async, unsafe, FFI, concurrency, crypto…
rust-intel
Hard rules for writing Rust in code that already compiles and passes tests but is silently broken, slow, or semver-fragile. Load this BEFORE writing any Rust code. Targets bugs that survive rustc, clippy, and cargo test but fail in production or rot the codebase. Covers async, unsafe, FFI, concurrency, crypto…
skill-audit
Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review.
agent-review
Critically review a Stencila agent and suggest improvements. Use when asked to review, audit, critique, evaluate, or improve an agent directory or AGENT.md file. Covers frontmatter validation, system instruction quality, configuration correctness, and adherence to the Agent schema.
critical-code-reviewer
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.