claude-delegate-local-mcp: Skill for Claude Code

.claude/skills/session-execute/SKILL.md

session-execute is a skill for Claude Code from ComputerSaysNull/claude-delegate-local-mcp. It costs 66 tokens per session (2,209 once invoked), scanned A, original, MIT.

A workflow guide for carrying out an approved coding plan, including parallel work, testing, commits, and pull requests. A pull request is a proposed set of code changes for review before merging.

In plain words
What is it for?
It helps execute planned repository changes, coordinate independent tasks, run test suites safely, make commits, and publish pull requests.
Why use it?
It prevents work from starting without an approved plan and defines how to handle conflicts, tests, bugs, and completion records.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the AskUserQuestion tool.

This is ComputerSaysNull/claude-delegate-local-mcp's own configuration. It tells Claude Code how to work on claude-delegate-local-mcp 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 claude-delegate-local-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ComputerSaysNull/claude-delegate-local-mcp. 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/ComputerSaysNull/claude-delegate-local-mcp/main/.claude/skills/session-execute/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ComputerSaysNull/claude-delegate-local-mcp

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 session-execute

README.md
[![agentmods](https://agentmods.dev/badge/skills/computersaysnull/claude-delegate-local-mcp/session-execute/github.svg)](https://agentmods.dev/skills/computersaysnull/claude-delegate-local-mcp/session-execute)
Your own site
<a href="https://agentmods.dev/skills/computersaysnull/claude-delegate-local-mcp/session-execute"><img src="https://agentmods.dev/badge/skills/computersaysnull/claude-delegate-local-mcp/session-execute/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 session-execute

Your own site · 80×15
<a href="https://agentmods.dev/skills/computersaysnull/claude-delegate-local-mcp/session-execute"><img src="https://agentmods.dev/badge/skills/computersaysnull/claude-delegate-local-mcp/session-execute.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,209 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 $0.00066 $0.02209
Opus 5.5 $0.00026 $0.00884
Sonnet 5.5 $0.00013 $0.00442
Haiku 4.5 $0.00007 $0.00221

Measured 5d ago against content hash 3e5ffae7af89, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

session-execute 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 5d 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/session-execute/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session execute

The plan was approved. session-plan stopped here on purpose; this is what it was stopping for.

If you cannot find the approved plan, stop and say so. Reconstructing it from the conversation produces something nobody approved, and the difference is invisible afterwards.

Read the hand-off notebook in the plans directory before the first edit. It says what this machine is set to that the repository does not, and it is the only place that knows.

1. What may run at once

Overlap what is genuinely independent — wall-clock is worth having — but the limits here are not about compute:

  • Delegations and delegated agents overlap freely, whether they read or write.
  • Never a suite while a fan-out is live. The server shares this machine.
  • Every commit edits the top of CHANGELOG.md, so two items built in parallel conflict there even when nothing else they touch does.

A worktree lets a suite run while work continues, with PYTHONPATH set. conftest.py puts the worktree's src/ first, but a test that starts a subprocess never runs it and imports the main checkout through the editable install; PYTHONPATH=<worktree>/src makes both import the worktree. Ignored config files must be copied in or tests that need them skip — the notebook has this machine's paths.

What spends the window is what enters this conversation, and that is as true of writing a module as of reading one. Quote a suite's tail rather than pasting its whole run.

2. Closing out a commit

In order, every time:

  1. Full suite, plus ruff and mypy. Targeted runs are the right tool while you iterate; the full suite is what closes a commit, because a targeted run cannot see the coupling a change creates. What has to be green is what lands: a branch is squash-merged, so that is its tip rather than every intermediate commit. ruff format is not a gate here; ruff check is, and so is mypy src, which CI's lint job runs too. It imports nothing, so it can run beside a suite; a second warm, a minute cold.
  2. The CHANGELOG entry, written to CHANGELOG.md's own header — it states the heading shape, the subsections and what an entry has to carry, and restating that here is how the two would come to disagree. The heading's number is provisional at this point; §4 is where it gets checked.
  3. The owning document, from python scripts/docs_gate.py --owner <path> and never from memory. Changing the code means updating its owner in the same commit.
  4. python scripts/docs_gate.py --mode pre-commit, with the change staged. Confirm it is staged first — git diff --cached --name-only must print at least one path. With nothing staged the gate prints 0 file(s) changed and then PASS, having run no ownership check at all, and that pass is indistinguishable from a real one.
  5. PLAN.md: flip the marker and change nothing else in that document. A ✅ body is frozen — no rewording, no line added or removed. A parent goes ✅ only once all its children are.
  6. The hand-off notebook: delete before you add. Remove every line this commit just filed into CHANGELOG.md, DECISIONS.md, JOURNAL.md or PLAN.md, then add only what is still unfiled. The notebook holds what an upcoming session needs and nothing a tracked document already has, so it shrinks as work lands.

Read the full file on GitHub · 159 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. 5d ago Changed · -4 lines 3e5ffae7af89
  2. 1mo ago Changed · +1 lines e87f59ccfe86
  3. 1mo ago Changed · +1 lines 28f2ad8610f6
  4. 1mo ago Changed · +7 lines 8eb80421f892
  5. 1mo ago Changed · +21 lines ecdcfe7f1b97
  6. 1mo ago First seen · 133 lines · 66 tokens per session scan A af310f7202c4

Subscribe to this mod's changes

session-execute is a skill published in the GitHub repository ComputerSaysNull/claude-delegate-local-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 2,209 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-15.