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-from-pr-learnings)<a href="https://agentmods.dev/skills/davidteren/intent-engineering/ie-from-pr-learnings"><img src="https://agentmods.dev/badge/skills/davidteren/intent-engineering/ie-from-pr-learnings/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/davidteren/intent-engineering/ie-from-pr-learnings"><img src="https://agentmods.dev/badge/skills/davidteren/intent-engineering/ie-from-pr-learnings.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00074 | $0.01476 |
| Opus 5 | $0.00037 | $0.00738 |
| Sonnet 5 | $0.00015 | $0.00295 |
| Haiku 4.5 | $0.00007 | $0.00148 |
Grade A, and why
ie-from-pr-learnings 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 9d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent Engineering — From PR learnings
Mines review learnings (PR threads, triage tables, or human-written guardrail lists)
into project .intense/ config so later /ie-review and /ie-audit runs enforce
what humans already fought for in review.
This skill writes only under .intense/ (and optional report under the resolved
artifacts.report_dir). It never pushes, never opens PRs, and never clobbers existing
YAML without confirmation.
When to use
- User has a triage doc (e.g.
PR-COMMENTS-TRIAGE-*.mdwith G1…Gn guardrails). - User points at one or more GitHub PRs after review.
- User wants workspace-level config for a multi-repo stack (BE + FE) via walk-up.
Argument parsing
| Token | Effect |
|---|---|
path ending in .md |
Treat as triage / learnings document (primary). |
pr:<url|number> |
Fetch review threads with gh (read-only). Repeatable. |
stack / blank with multi-repo cwd |
Prefer nearest .intense/ walk-up; detect BE/FE siblings. |
config:<path> |
Override project config dir (same rules as config-resolution). |
out:<dir> |
Write the summary report under this dir (default: resolved artifacts.report_dir). |
Procedure
1. Resolve project base + existing config
Per ${CLAUDE_PLUGIN_ROOT}/references/config-resolution.md:
- Discover
PROJECT_INTENSE(walk-up /config:/INTENSE_CONFIG_DIR). - If none, create
.intense/at the workspace root (for multi-repo stacks, the parent that contains backend/frontend-style siblings, not deep inside one app) after confirming with the user. - Load existing
ways-of-working.yaml/patterns.yaml/thresholds.yamlif present. - Always record Config source for the report.
2. Collect learnings
From a triage markdown (preferred when available):
- Extract tables of guardrails (IDs like
G1…, priority P0–P3, state). - Prefer rows marked P0/P1 and cross-stack guardrails.
- Capture “Wontfix + rationale” as advisory notes (do not invent severity P0).
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.
- 9d ago First seen · 133 lines · 74 tokens per session scan A 6f64b23c99b1
ie-from-pr-learnings is a skill published in the GitHub repository davidteren/intent-engineering (3 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 1,476 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
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…
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.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
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.