actual-mcp-server: Skill for Claude Code

.claude/skills/implement-ticket/SKILL.md

implement-ticket is a skill for Claude Code from agigante80/actual-mcp-server. It costs 162 tokens per session (3,312 once invoked), scanned A, original, MIT.

An end-to-end workflow for implementing a numbered GitHub issue in actual-mcp-server, from making the issue ready to build through review, testing, commit, and push.

In plain words
What is it for?
Use it when you want a specific issue implemented, validated, reviewed, and delivered with version and continuous-integration checks.
Why use it?
It gives the work a repeatable sequence and handles discovered problems by fixing them or creating follow-up issues. It keeps implementation on the develop branch rather than main.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: mentions CLAUDE.md; mentions subagents; names the TodoWrite tool.

This is agigante80/actual-mcp-server's own configuration. It tells Claude Code how to work on actual-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything actual-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to agigante80/actual-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/agigante80/actual-mcp-server/main/.claude/skills/implement-ticket/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/agigante80/actual-mcp-server

Made for: Claude Code.

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 implement-ticket

README.md
[![agentmods](https://agentmods.dev/badge/skills/agigante80/actual-mcp-server/implement-ticket.svg)](https://agentmods.dev/skills/agigante80/actual-mcp-server/implement-ticket)
Your own site
<a href="https://agentmods.dev/skills/agigante80/actual-mcp-server/implement-ticket"><img src="https://agentmods.dev/badge/skills/agigante80/actual-mcp-server/implement-ticket.svg" alt="Measured on agentmods" height="20"></a>
Per session 162 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,312 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 98
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00162 $0.03312
Opus 5 $0.00081 $0.01656
Sonnet 5 $0.00032 $0.00662
Haiku 4.5 $0.00016 $0.00331

Measured 8d ago against content hash fa2eaf1023dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

implement-ticket 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 8d 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.

.claude/skills/implement-ticket/SKILL.md · 256 lines

How it starts

The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement Ticket

A repeatable pipeline that takes a GitHub issue number and carries it from "ready to build" to "merged on develop", with adversarial review and automatic follow-up ticketing baked in. It chains tools we already have (the ticket-gate agent, the project validation sequence, /code-review, /local-env) so a single instruction does what a careful engineer would do across an afternoon.

When this runs

Trigger on any request to implement a specific issue by number. Extract the issue number from the prompt. If no number is present, ask for one before starting. Everything happens on develop; never touch main (see CLAUDE.md).

Inputs and state to track

  • TICKET: the issue number under implementation.
  • DEPTH: recursion depth, starts at 0 for the user-invoked ticket. Spinning off and auto-implementing a discovered ticket increments it. The cap is 2.
  • SEEN: the set of ticket numbers this run has already started, so a follow-up ticket can never re-enter a ticket already in progress (loop guard).

Hold these in a TodoWrite list so progress survives a long run.

The pipeline

Run the phases in order. A phase that cannot pass after its bounded retries stops the run with a clear report rather than limping forward.

Order depends on ticket type. For a bug, behaviour-change, or external / fork-harvested ticket, run Phase 0 (Reproduce) BEFORE Phase 1 (Gate): gating, security-reviewing, and synthesising a ticket that turns out to be a phantom is wasted work, so prove it reproduces first and gate only what survives. For greenfield features, docs, and chore/CI tickets (nothing to reproduce), skip Phase 0 and start at Phase 1.

Phase 0: Reproduce first (bug, behaviour-change, and external/fork tickets)

Run this FIRST, ahead of the gate, when the ticket is labelled bug, proposes a change to existing observable behaviour, OR is external / community / fork-harvested. Skip it only for greenfield features with nothing to reproduce, docs, and chore/CI tickets (say so in the report, then start at Phase 1).

Read the full file on GitHub · 256 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. 8d ago First seen · 256 lines · 162 tokens per session scan A fa2eaf1023dd

Subscribe to this mod's changes

implement-ticket is a skill published in the GitHub repository agigante80/actual-mcp-server (50 stars, last pushed yesterday), licensed MIT. It adds 162 tokens to every session and 3,312 once invoked, about $0.0008 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.