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.
curl -O https://raw.githubusercontent.com/ComputerSaysNull/claude-delegate-local-mcp/main/.claude/skills/session-execute/SKILL.mdgit clone --depth 1 https://github.com/ComputerSaysNull/claude-delegate-local-mcpWrote 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.
[](https://agentmods.dev/skills/computersaysnull/claude-delegate-local-mcp/session-execute)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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:
- 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 formatis not a gate here;ruff checkis, and so ismypy src, which CI's lint job runs too. It imports nothing, so it can run beside a suite; a second warm, a minute cold. - 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. - 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. python scripts/docs_gate.py --mode pre-commit, with the change staged. Confirm it is staged first —git diff --cached --name-onlymust print at least one path. With nothing staged the gate prints0 file(s) changedand then PASS, having run no ownership check at all, and that pass is indistinguishable from a real one.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.- The hand-off notebook: delete before you add. Remove every line this commit just
filed into
CHANGELOG.md,DECISIONS.md,JOURNAL.mdorPLAN.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.
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.
- 5d ago Changed · -4 lines 3e5ffae7af89
- 1mo ago Changed · +1 lines e87f59ccfe86
- 1mo ago Changed · +1 lines 28f2ad8610f6
- 1mo ago Changed · +7 lines 8eb80421f892
- 1mo ago Changed · +21 lines ecdcfe7f1b97
- 1mo ago First seen · 133 lines · 66 tokens per session scan A af310f7202c4
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.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
repo-sync
Manage automatic Git syncing on macOS with repo-sync. Use only when the user explicitly invokes /repo-sync.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…