agentmods.dev

upload

upload is a skill for Claude Code, Codex from drafthq/draft. It costs 32 tokens per session (1,084 once invoked), scanned A, original, MIT.

A final review gate for handing a Draft track to a human through a git upload, push, or pull request. It checks review results, required approvals, deployment readiness, and validator results before submission.

In plain words
What is it for?
Use it before pushing a completed track or opening a pull request. It verifies that the track has passed review and that the required release checks are clear.
Why use it?
It prevents incomplete or blocked work from being uploaded for review. It also catches missing reviews, approvals, deployment checks, or code-quality and citation problems.

Skill for Claude CodeCodex

Part of the draft plugin — 33 skills, 7 agents shipped together

not rated 40 16d ago A scan 32 tokens original MIT
View the source file drafthq/draft
Install

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.

agentmods
npx agentmods add skills/drafthq/draft/upload
Any agent
npx skills add drafthq/draft --skill upload
Clone the repo
git clone --depth 1 https://github.com/drafthq/draft

Made for: Claude Code, Codex.

Or install draft, the plugin that ships this one along with the rest of its 33 skills, 7 agents.

Wrote 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.

agentmods badge for upload

README.md
[![agentmods](https://agentmods.dev/badge/skills/drafthq/draft/upload.svg)](https://agentmods.dev/skills/drafthq/draft/upload)
Your own site
<a href="https://agentmods.dev/skills/drafthq/draft/upload"><img src="https://agentmods.dev/badge/skills/drafthq/draft/upload.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,084 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00032 $0.01084
Opus 5 $0.00016 $0.00542
Sonnet 5 $0.00006 $0.00217
Haiku 4.5 $0.00003 $0.00108

Measured 4d ago against content hash f4e9479623ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

upload 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.

skills/upload/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Upload for Review

Gate track completion before git upload, git push, or opening a PR for human review.

Red Flags — STOP if you're

See shared red flags.

Skill-specific:

  • Uploading without a passing /draft:review on the track
  • Skipping HLD §Approvals for criticality ∈ {high, mission-critical} tracks
  • Treating a deploy checklist with status: BLOCKED as passing
  • Pushing when validator tools report hygiene or citation drift

Upload is a gate, not a shortcut around review.

Step 1: Resolve Track

  1. Parse track <id|name> from arguments, or auto-detect the active [~] track from draft/tracks.md.
  2. Load draft/tracks/<id>/spec.md, plan.md, metadata.json, and hld.md when present.
  3. If no track resolves, error: "No track to upload. Specify track <id> or activate a track."

Step 2: Pre-Upload Verification

2.1 Review gate

  • Require review-report-latest.md on the track with verdict PASS or PASS WITH NOTES.
  • If missing or FAIL, stop and instruct: run /draft:review track <id> first.

2.2 Deploy checklist (auto-invoke)

Run /draft:deploy-checklist track <id> when no fresh passing checklist exists.

2.5 Checklist status

  • Read draft/tracks/<id>/deploy-checklist-latest.md (or timestamped sibling).
  • If frontmatter contains status: BLOCKED, stop — checklist is not a passing gate.
  • Critical unchecked items block upload.

2.3 Validator chain

Run the WS-9 chain from verification-gates.md against the track directory. Any non-zero exit aborts upload.

TRACK_DIR="draft/tracks/<id>"
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"

"$DRAFT_TOOLS/check-track-hygiene.sh" "$TRACK_DIR"
"$DRAFT_TOOLS/verify-citations.sh" "$TRACK_DIR"
"$DRAFT_TOOLS/verify-doc-anchors.sh" "$TRACK_DIR"
"$DRAFT_TOOLS/diff-templates-vs-tracks.sh" "$TRACK_DIR"

Read the full file on GitHub · 120 lines

Changes

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.

  1. 4d ago First seen · 120 lines · 32 tokens per session scan A f4e9479623ae

Subscribe to this mod's changes

upload is a skill published in the GitHub repository drafthq/draft (40 stars, last pushed 16d ago), licensed MIT. It adds 32 tokens to every session and 1,084 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.

Git and workflowPlanningReleasesai-code-reviewai-codingclaude-codecopilotcursor
Related

Other skills, from other repositories

release-swift

Cut a release of OpenUsage (Swift menu-bar app): pick a version, generate a categorized changelog, tag from main, and publish the GitHub Release with notes. Use to ship an Early Access beta or a stable release.

robinebers/openusage · 0 tokens

macos-packaging-notarization

Prepare macOS packaging and notarization workflows. Use when archiving apps, validating bundles, or explaining distribution-only failures.

robinebers/openusage · 32 tokens

memorix-memory

Use when prior workspace context, past decisions, solved bugs, handoff state, or durable project knowledge would help a coding task.

AVIDS2/memorix · 30 tokens

memorix

Use when Claude Code needs Memorix shared memory, reasoning, Git Memory, mini-skills, session handoff, orchestration coordination, or integration troubleshooting.

AVIDS2/memorix · 34 tokens

memorix-mini-skills

Use when durable project knowledge, gotchas, workflows, or repeated fixes should become reusable agent guidance instead of ordinary memory.

AVIDS2/memorix · 30 tokens

memorix-orchestrate

Use when a main agent needs Memorix to coordinate explicit subagent work through tasks, handoffs, messages, file locks, or the orchestrate CLI.

AVIDS2/memorix · 37 tokens