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/jazz1x/harnish/drafti-featurenpx skills add jazz1x/harnish --skill drafti-featuregit clone --depth 1 https://github.com/jazz1x/harnishWrote 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/jazz1x/harnish/drafti-feature)<a href="https://agentmods.dev/skills/jazz1x/harnish/drafti-feature"><img src="https://agentmods.dev/badge/skills/jazz1x/harnish/drafti-feature.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 | $0.00125 | $0.01914 |
| Opus 5 | $0.00063 | $0.00957 |
| Sonnet 5 | $0.00025 | $0.00383 |
| Haiku 4.5 | $0.00013 | $0.00191 |
Grade A, and why
drafti-feature scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
drafti-feature — Planning to Implementation Spec PRD
Takes planning requirements and produces an implementation spec PRD focused on "how to build it."
Bash Convention
Each Bash tool invocation is a fresh subshell. Every bash block re-declares HARNISH_ROOT="${CLAUDE_PLUGIN_ROOT}" inline; no persistent variables.
Skill Chain
Can be invoked independently (planning doc required). Follow-up: "start implementation after review" → impl, or "/galmuri:ralphi to verify PRD consistency" → galmuri:ralphi (sibling plugin).
Step 1: Requirement Parsing
Extract 4 items from the planning document:
| Item | Content |
|---|---|
| Core Feature | User-visible changes (1~3 lines) |
| Success Metrics | KPI/goals (numeric or conditional) |
| User Flow | Happy path + branches |
| Non-Functional Requirements | Performance, security, accessibility |
Gate: all 4 items must be present before proceeding.
- 0 missing → proceed to Step 2.
- 1+ missing → ask the user for the missing items. Do not assume defaults. Re-evaluate after the user replies; if still missing → re-ask.
Step 2: Existing Asset Query
Extract 3~5 core keywords, then:
HARNISH_ROOT="${CLAUDE_PLUGIN_ROOT}"
if [[ -n "$HARNISH_ROOT" ]]; then
bash "$HARNISH_ROOT/scripts/query-assets.sh" \
--tags "{keywords}" --format inject \
--base-dir "$(pwd)/.harnish"
fi
If assets found, use as reference; if none, proceed anyway.
Step 3: Codebase Exploration
Detect the language from project config files (package.json, pyproject.toml, go.mod, etc.), then explore affected files using core keywords.
- Keyword search: Find related code files
- Filename patterns: Find related components/modules
- Data models: Find type definitions/interfaces/classes
Result: Affected file list + whether data model changes are needed → reflect in PRD §4.
Step 4: Feature Flag Assessment (Optional)
Not all features need a flag. Design one only when the conditions below apply.
What ships with it
5 files 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.
- 4d ago First seen · 194 lines · 125 tokens per session scan A 7c40451c9dc7
drafti-feature is a skill published in the GitHub repository jazz1x/harnish (4 stars, last pushed 3mo ago), licensed MIT. It adds 125 tokens to every session and 1,914 once invoked, about $0.0006 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
complete-partial-pr
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.
google-drive-sheets
Find, read, export, edit, and manage the user's Google Drive, Docs, Sheets, and Slides through per-user OAuth.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
portfolio
Cross-chain DeFi portfolio discovery, rebalancing suggestions, and NEAR Intent construction. Activates when the user pastes a wallet address or asks about yield/positions/rebalancing. Bootstraps a per-user "portfolio" project, aggregates positions across all the user's addresses inside one project, and offers a…