specgate-work-delivery

specgate-work-delivery is a skill for Claude Code from thanhtung2693/specgate. It costs 38 tokens per session (1,780 once invoked), scanned A, original, Apache-2.0.

A delivery workflow for carrying out an approved SpecGate work item. SpecGate is a system for defining, preparing, and tracking software work before it is implemented.

In plain words
What is it for?
Use it to load the approved work instructions, check who should act next, implement the allowed changes, and provide updated evidence for review.
Why use it?
It prevents coding from starting when approval, requirements, context, or success checks are missing or out of date.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the specgate plugin — 4 skills, 1 hook shipped together

Good fit Use it to load the approved work instructions, check who should act next, implement the allowed changes, and provide updated evidence for review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thanhtung2693/specgate/specgate-work-delivery
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.

Any agent
npx skills add thanhtung2693/specgate --skill specgate-work-delivery
Clone the repo
git clone --depth 1 https://github.com/thanhtung2693/specgate

Made for: Claude Code.

Or install specgate, the plugin that ships this one along with the rest of its 4 skills, 1 hook.

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 specgate-work-delivery

README.md
[![agentmods](https://agentmods.dev/badge/skills/thanhtung2693/specgate/specgate-work-delivery/github.svg)](https://agentmods.dev/skills/thanhtung2693/specgate/specgate-work-delivery)
Your own site
<a href="https://agentmods.dev/skills/thanhtung2693/specgate/specgate-work-delivery"><img src="https://agentmods.dev/badge/skills/thanhtung2693/specgate/specgate-work-delivery/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.

agentmods 80×15 button for specgate-work-delivery

Your own site · 80×15
<a href="https://agentmods.dev/skills/thanhtung2693/specgate/specgate-work-delivery"><img src="https://agentmods.dev/badge/skills/thanhtung2693/specgate/specgate-work-delivery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,780 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00038 $0.01780
Opus 5 $0.00019 $0.00890
Sonnet 5 $0.00008 $0.00356
Haiku 4.5 $0.00004 $0.00178

Measured 2d ago against content hash 8d1f82d9f2d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

specgate-work-delivery 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 2d 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.

app/cli/internal/command/local_plugin_assets/skills/specgate-work-delivery/SKILL.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delivering Work

Apply the SpecGate operating contract. Implement the approved contract, stop at the next actor, and never approve an artifact or make a human delivery decision.

1. Load the exact contract

Use the mode from doctor. Local: read scope, criteria, verification contract, document index, and status together:

specgate work resume "$WORK_REF" --json

Use data.status. Read pinned documents, including scope and non-goals:

specgate work context "$WORK_REF" --document "$DOCUMENT_PATH" --role "$ROLE" --json

Copy path/role from data.documents. Reuse only matching-digest content; the index cannot replace it. Quick work uses persisted scope/criteria.

Full mode: read these; status is change status.data:

specgate work context "$WORK_REF" --json
specgate change status "$WORK_REF" --json

Stop before editing when approval is absent, the Context Pack is stale, or criteria are missing/placeholders. Hand artifact-backed work missing its approved version to the human or specgate-work-preparation.

Reuse results until state changes; avoid duplicate reads. Follow status:

  • If data.next_actor is not implementing_agent, hand off without editing.
  • For review_pending, accept only one specgate next_command without shell operators; else hand off. Run it verbatim before sections 2–5. On failure, go to section 7. On success, reread Change status; stop if still review_pending.
  • For rework_requested, carry guidance and missing through: focused fix, affected checks, updated evidence, submit, fresh status. Never submit old evidence first.
  • Otherwise record missing and guidance, then follow next_command's named section or stop if none matches.

Every change/check must map to a criterion or required repository-doc update.

Completion criterion: submitted evidence contains an observed result for every required check, or its explicit skip reason.

2. Resume safely

Read the full file on GitHub · 192 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. 2d ago Changed · -1 lines 8d1f82d9f2d9
  2. 8d ago First seen · 193 lines · 38 tokens per session scan A 20702c7095a9

Subscribe to this mod's changes

specgate-work-delivery is a skill published in the GitHub repository thanhtung2693/specgate (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 38 tokens to every session and 1,780 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 2026-08-31.

Related

Other skills, from other repositories

coding-agents-farm

To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.

griddynamics/rosetta · 32 tokens

delegate-coding-agent

Route coding work to another local coding-agent CLI through the llm-provider MCP server. Use when a task benefits from a powerful model for difficult reasoning or a faster, lower-cost model for bounded implementation, tests, investigation, or review.

manishiitg/llm-provider-mcp · 52 tokens

trial

A pre-delivery evidence gate for coding agents. Hold the final response as a private draft, judge every user-visible claim against fresh covering receipts, and release only verified results. Use when unsupported completion claims, shallow green tests, stale evidence, or high-risk changes must not reach the user.

Da7-Tech/trial · 60 tokens

implementation-loop

Disciplined plan-build-verify loop for implementing a feature or change. Use when building something new or modifying existing behavior, especially across multiple files.

KingEmma7/cursor-os · 33 tokens

debugging-loop

Systematic reproduce-isolate-fix-verify loop for bugs, test failures, and unexpected behavior. Use when something is broken and the cause is not yet known.

KingEmma7/cursor-os · 37 tokens

trial

Trial — a pre-delivery evidence gate. Use before every final response about code or file changes: hold it as a private draft, judge every user-visible claim against fresh covering receipts, and release only verified results.

Da7-Tech/trial · 45 tokens