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/graphnpx skills add drafthq/draft --skill graphgit 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 | $0.00056 | $0.01378 |
| Opus 5 | $0.00028 | $0.00689 |
| Sonnet 5 | $0.00011 | $0.00276 |
| Haiku 4.5 | $0.00006 | $0.00138 |
Grade A, and why
graph scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft Graph
Initialize or refresh the draft/graph/ knowledge-graph snapshot for a single repository. This is the narrow "give me a fresh structural graph" command — it does not generate architecture.md/.ai-context.md and does not re-inject doc diagram slots (both are /draft:init). For scope-aware, root-first graph memory across a monorepo (root spine + module→root links), use /draft:init --graph-only.
Red Flags - STOP if you're
- Reporting counts without actually running
graph-snapshot.sh - Claiming the graph is built when the engine was unavailable
- Treating an engine-unavailable result as a hard failure (it degrades gracefully)
- Running against a path that isn't a directory
Build, then report what the tools actually returned.
Step 1: Resolve the target repo
The command takes an optional path argument: /draft:graph [path].
- No argument → use the current directory (
.). - With a path → use it as the repo root.
REPO="${1:-.}"
if [ ! -d "$REPO" ]; then
echo "ERROR: '$REPO' is not a directory."
exit 1
fi
REPO_ABS="$(cd "$REPO" && pwd)"
echo "Target repo: $REPO_ABS"
# Locate Draft's bundled helpers. Skills run with cwd = the user's project and
# ${CLAUDE_PLUGIN_ROOT} is not exported into skill Bash, so resolve DRAFT_TOOLS here
# and call helpers as "$DRAFT_TOOLS/<tool>.sh". 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"
DRAFT_SCRIPTS="${DRAFT_TOOLS%/tools}" # parent dir holds fetch-memory-engine.sh
Step 2: Ensure the engine is present
Resolve the engine; if it is missing, fetch it once, then re-check. If it is still unavailable (e.g. offline, opted out via DRAFT_MEMORY_DISABLE), report and stop gracefully — graph features are optional everywhere in Draft.
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 · 117 lines · 56 tokens per session scan A d9eaccdbc45c
graph is a skill published in the GitHub repository drafthq/draft (40 stars, last pushed 13d ago), licensed MIT. It adds 56 tokens to every session and 1,378 once invoked, about $0.0003 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.