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/drafthq/draft/adrnpx skills add drafthq/draft --skill adrgit clone --depth 1 https://github.com/drafthq/draftWhat 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 | $0.00037 | $0.03324 |
| Opus 5 | $0.00018 | $0.01662 |
| Sonnet 5 | $0.00007 | $0.00665 |
| Haiku 4.5 | $0.00004 | $0.00332 |
Grade A, and why
adr 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 yesterday.
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 — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Decision Records
You are creating or managing Architecture Decision Records (ADRs) for this project.
Red Flags - STOP if you're
- Creating an ADR without understanding the decision context
- Documenting trivial decisions that don't warrant an ADR (e.g., variable naming)
- Writing an ADR after the fact without capturing the original reasoning
- Listing alternatives without genuine pros/cons analysis
- Skipping the "Consequences" section (the most valuable part)
- Not checking existing ADRs for conflicts or superseded decisions
ADRs capture WHY, not just WHAT. Every decision needs alternatives considered.
Pre-Check
- Verify Draft is initialized:
ls draft/ 2>/dev/null
If draft/ doesn't exist:
- Tell user: "Project not initialized. Run
/draft:initfirst." - Stop here.
- Check for existing ADR directory:
ls draft/adrs/ 2>/dev/null
If draft/adrs/ doesn't exist, create it:
mkdir -p draft/adrs
Step 1: Parse Arguments
Check for arguments:
/draft:adr— Interactive mode: ask about the decision/draft:adr "decision title"— Create ADR with given title/draft:adr list— List all existing ADRs/draft:adr supersede <number>— Mark an ADR as superseded
List Mode
If argument is list:
-
Prefer the deterministic
adr-index.shwrapper for the listing — it returns a structured JSON{adrs:[{id,title,date,status,path,related_tracks}]}derived from each ADR's frontmatter. Resolve via the canonical tool resolver (see core/shared/tool-resolver.md):DRAFT_TOOLS="${DRAFT_PLUGIN_ROOT:-$(cat ~/.cache/draft/plugin-root 2>/dev/null)}/scripts/tools" [ -d "$DRAFT_TOOLS" ] || DRAFT_TOOLS="$(ls -d ~/.claude/plugins/cache/*/draft/*/scripts/tools 2>/dev/null | sort -V | tail -1)" [ -d "$DRAFT_TOOLS" ] || DRAFT_TOOLS="$(ls -d ~/.claude/plugins/marketplaces/*draft*/scripts/tools 2>/dev/null | tail -1)" [ -d "$DRAFT_TOOLS" ] || DRAFT_TOOLS="$PWD/scripts/tools" if [ -x "$DRAFT_TOOLS/adr-index.sh" ]; then bash "$DRAFT_TOOLS/adr-index.sh" --root draft/adrs else ls draft/adrs/ # fallback: enumerate files manually fi
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.
- yesterday First seen · 394 lines · 37 tokens per session scan A 05046bb28f2a
adr is a skill published in the GitHub repository drafthq/draft (40 stars, last pushed 13d ago), licensed MIT. It adds 37 tokens to every session and 3,324 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
memorix-memory
Use when prior workspace context, past decisions, solved bugs, handoff state, or durable project knowledge would help a coding task.
memorix
Use when Claude Code needs Memorix shared memory, reasoning, Git Memory, mini-skills, session handoff, orchestration coordination, or integration troubleshooting.
memorix-mini-skills
Use when durable project knowledge, gotchas, workflows, or repeated fixes should become reusable agent guidance instead of ordinary memory.
memorix-orchestrate
Use when a main agent needs Memorix to coordinate explicit subagent work through tasks, handoffs, messages, file locks, or the orchestrate CLI.
memorix-reasoning
Use when a technical decision, trade-off, rejected alternative, architecture rationale, or design risk should be recorded or recovered.
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.