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-auditnpx skills add davidteren/intent-engineering --skill ie-auditgit 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-audit)<a href="https://agentmods.dev/skills/davidteren/intent-engineering/ie-audit"><img src="https://agentmods.dev/badge/skills/davidteren/intent-engineering/ie-audit.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 | $0.00087 | $0.01905 |
| Opus 5 | $0.00044 | $0.00953 |
| Sonnet 5 | $0.00017 | $0.00381 |
| Haiku 4.5 | $0.00009 | $0.00191 |
Grade B, and why
ie-audit scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
`${CLAUDE_PLUGIN_ROOT}/references/config-resolution.md` (only `rm -rf` when Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent Engineering — Codebase Audit
Assesses the intent-engineering posture of existing code (no diff). Where
ie-review judges a change, ie-audit judges a body of code: how predictable,
conventional, simple, and usable it is today, scored per dimension with the worst gaps
surfaced first. This is a read-only assessment — it never edits code.
Argument parsing
| Token | Effect |
|---|---|
mode:agent |
Emit JSON instead of markdown. |
out:<path> |
Override published report path (file or dir). Defaults: scratch .intense/runs/<run-id>/, publish docs/intent-engineering/<stamp>-audit[-scope].md. |
config:<path> |
Override project config directory (walk-up / INTENSE_CONFIG_DIR otherwise). |
| remainder | Path, glob, or named subsystem/feature to audit. Default: the repo (excluding deps, build output, generated, and vendored dirs). |
Stage 1 — Scope the target
Resolve the audit set. Be explicit and bounded:
- Determine the file set: the given path/glob, or the repo's source dirs. Exclude
node_modules,vendor,dist/build, generated files, lockfiles, and artifact dirs (resolvedartifacts.run_dir,artifacts.report_dir, legacywip/,.intense/runs/,docs/intent-engineering/). - Detect the stack(s) via
${CLAUDE_PLUGIN_ROOT}/references/stack-catalog.md(Detection signals); load matchingframeworks/<stack>.mddocs. Do not hardcode a closed stack list. - Sampling rule (large targets). If the set exceeds what lenses can read closely (rough guide: > ~40 files or very large files), select a representative sample: the highest-churn / largest / most-depended-on files plus the public entry points and a cross-section of each layer. State the sampling explicitly — what was and wasn't covered goes in Coverage. Never silently truncate and imply full coverage.
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 are authoritative, and thresholds + pattern policy feed the
architecture lens. Always state the Config source in Coverage (never silent
defaults). Then read ${CLAUDE_PLUGIN_ROOT}/references/lens-catalog.md and
${CLAUDE_PLUGIN_ROOT}/references/stack-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 · 135 lines · 87 tokens per session scan B e08232742b1a
ie-audit is a skill published in the GitHub repository davidteren/intent-engineering (3 stars, last pushed 20d ago), licensed MIT. It adds 87 tokens to every session and 1,905 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). 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…
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…
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…
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…
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…