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-plan/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-plan)<a href="https://agentmods.dev/skills/computersaysnull/claude-delegate-local-mcp/session-plan"><img src="https://agentmods.dev/badge/skills/computersaysnull/claude-delegate-local-mcp/session-plan/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-plan"><img src="https://agentmods.dev/badge/skills/computersaysnull/claude-delegate-local-mcp/session-plan.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 | $0.00071 | $0.02317 |
| Opus 5.5 | $0.00028 | $0.00927 |
| Sonnet 5.5 | $0.00014 | $0.00463 |
| Haiku 4.5 | $0.00007 | $0.00232 |
Grade A, and why
session-plan 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 27d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session plan
Five steps. Step 4 is not optional and step 5 is where you stop. Execution is a different skill — session-execute — and nothing here starts work. Read it to understand what it needs from the plan you are about to write.
1. Read. Do not edit.
PLAN.md is the contract. If it is not there, stop and say so rather than planning from
memory or from another document: there is no fallback, and a session planned against the
wrong source is worse than one not planned at all. STATUS.md was retired — it does not
exist, do not look for it.
For why an item exists: DECISIONS.md. For what shipped and why: CHANGELOG.md. For what
was measured recently: the last few JOURNAL.md entries. For what an upcoming session needs
and no tracked document holds: the hand-off notebook in the plans directory.
Requests from the web viewer's repository are input too: changes it needs in the
transcript format or the feed, filed as open issues labelled "contract" in the planning
repository CLAUDE.local.md names. List them with gh issue list --label contract --state open and that repository passed as -R, and rank each with the ⬜ items, named in the
plan by its issue number. Never write that repository's name into a tracked file: it is
private.
Delegate the reading. delegate_readonly, one question per call, and name the documents in
files[]. Do not read them in the main conversation to answer what a delegation could
answer — that is what actually ends a session. If delegate_readonly is not available, use
the Explore agent.
2. Rank, then fill
🔄 outranks everything: finish before starting. Then rank the ⬜ items under Open by
blocking impact ÷ effort. ✅, ❌ and Deferred are out of scope for the ranking.
- An item resting on a claim nobody has measured is a spike, not an item. Rank the spike first, and say what would be run to settle it.
- Settle that spike now if its answer would move anything else. Ask: if the measurement came back the other way, would another item's viability or its order change? If yes, measure before the ranking is finished, or this step and the next are built on the very claim they exist to catch. If it only changes its own item's design, step 4 is soon enough.
- Rank every
⬜item. Ranking stops when the items run out, not when the list starts to look long enough.
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.
- 27d ago Changed · +7 lines ef6d2800d182
- 1mo ago Changed 431a877d1ce8
- 1mo ago Changed · +1 lines 7c8530bd510e
- 1mo ago Changed · +53 lines · +3 tokens per session 64cb72dc2477
- 1mo ago Changed · +10 lines · +9 tokens per session 4bdff474fbd5
- 1mo ago First seen · 87 lines · 59 tokens per session scan A ce8bcdf33131
session-plan is a skill published in the GitHub repository ComputerSaysNull/claude-delegate-local-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 2,317 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 2026-09-11.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.