actual-mcp-server: Skill for Claude Code

.claude/skills/working-overnight/SKILL.md

working-overnight is a skill for Claude Code from agigante80/actual-mcp-server. It costs 105 tokens per session (1,030 once invoked), scanned A, original, MIT.

A set of rules for allowing coding work to continue unattended overnight. It takes approved tickets or investigations, makes changes on branches, opens pull requests, and reports what happened without merging anything.

In plain words
What is it for?
Use it for governed overnight implementation work, security or full reviews that create tickets, and morning reports on completed, deferred, or blocked tasks.
Why use it?
It lets routine work progress while you are away while deferring decisions that require your judgment instead of guessing.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions subagents.

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/working-overnight/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 working-overnight

README.md
[![agentmods](https://agentmods.dev/badge/skills/agigante80/actual-mcp-server/working-overnight/github.svg)](https://agentmods.dev/skills/agigante80/actual-mcp-server/working-overnight)
Your own site
<a href="https://agentmods.dev/skills/agigante80/actual-mcp-server/working-overnight"><img src="https://agentmods.dev/badge/skills/agigante80/actual-mcp-server/working-overnight/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 working-overnight

Your own site · 80×15
<a href="https://agentmods.dev/skills/agigante80/actual-mcp-server/working-overnight"><img src="https://agentmods.dev/badge/skills/agigante80/actual-mcp-server/working-overnight.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,030 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 pass 7 Sept 2026
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 $0.00105 $0.01030
Opus 5 $0.00053 $0.00515
Sonnet 5 $0.00021 $0.00206
Haiku 4.5 $0.00011 $0.00103

Measured 12d ago against content hash 31362c1ac2b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

working-overnight 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 12d 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/working-overnight/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working overnight

Governed unattended work while the user is away. The engine is /loop: the user launches /loop working-overnight and each cycle does one unit of work and returns with fresh context. This skill holds the policy: what to pull, how to stay safe, when to defer, and when to wind down. The overnight-continue hook keeps a single cycle from halting on a question; it is not the engine.

Read references/safety.md (the tier model and the never-list) and references/pipeline.md (the per-task governance pipeline) before the first cycle. They are binding.

Two modes, told apart by the manifest

  • Pre-flight (interactive, once, when the user sets up the night): arm the run.
  • Cycle (each /loop iteration, unattended): do one unit of work.

If .claude/overnight/active.md is absent, this is pre-flight. If it is present, this is a cycle.

Pre-flight (arming)

Do this with the user present. Never start autonomous work until they confirm.

  1. Agree the work source and scope: which tickets, which investigations, and any no-go areas (paths, systems, ticket labels to avoid).
  2. Agree the budget (token or cost ceiling) and the investigation-depth cap (how many new tickets an investigation may create before implementation must catch up).
  3. Confirm the safety config in references/safety.md: the allowed tools and the Tier-3 never-list. Do not proceed if the requested work would need anything on the never-list.
  4. Ensure .claude/overnight/ is gitignored.
  5. Write the manifest to .claude/overnight/active.md (scope, budget, caps, no-go list, start time) and seed .claude/overnight/queue.md with the initial items. Creating the manifest arms the hook.
  6. Tell the user to run /loop working-overnight and leave. Stop here.

Cycle (one unit of work)

  1. Re-read .claude/overnight/active.md, .claude/overnight/queue.md, and the project rules (CLAUDE.md, whose coding standards are inline). Fresh every cycle: this is why rule-drift does not accumulate.
  2. Pick the next item by priority: a cleanly-gated ready ticket, else an ungated ticket to gate, else a bounded investigation. If no safe item remains, go to Wind-down.
  3. Classify the item by tier (references/safety.md). A Tier-3 action is never performed: park it as needs-human and pick another item.
  4. Resolve any question. Try web search, the code, and the project rules first. Only a genuine you-only decision blocks: if it is low-stakes and reversible, record the assumption for the report and continue; otherwise append it to .claude/overnight/decisions.md (item, options, your recommendation) and pick another item.
  5. Do the work through references/pipeline.md.
  6. Implementation lands in a per-item git worktree as a branch and a PR, never merged. Investigations write findings and create/gate tickets.
  7. Update .claude/overnight/queue.md (done, parked, or newly created items).
  8. Backstop: if context or the budget is near its limit, go to Wind-down now rather than starting another item.

Read the full file on GitHub · 80 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 80 lines · 105 tokens per session scan A 31362c1ac2b7

Subscribe to this mod's changes

working-overnight is a skill published in the GitHub repository agigante80/actual-mcp-server (54 stars, last pushed yesterday), licensed MIT. It adds 105 tokens to every session and 1,030 once invoked, about $0.0005 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.