Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add addit-digital/addit-harness --skill save-plangit clone --depth 1 https://github.com/addit-digital/addit-harnessWrote 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/addit-digital/addit-harness/save-plan)<a href="https://agentmods.dev/skills/addit-digital/addit-harness/save-plan"><img src="https://agentmods.dev/badge/skills/addit-digital/addit-harness/save-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/addit-digital/addit-harness/save-plan"><img src="https://agentmods.dev/badge/skills/addit-digital/addit-harness/save-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 | $0.00083 | $0.01215 |
| Opus 5.5 | $0.00033 | $0.00486 |
| Sonnet 5.5 | $0.00017 | $0.00243 |
| Haiku 4.5 | $0.00008 | $0.00121 |
Grade A, and why
save-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 24d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save plan — persist a plan to a viewable markdown file
The Claude Code CLI shows a ```mermaid block as raw code, never a rendered
diagram, and a plan presented in the CLI isn't saved anywhere convenient to open.
This skill writes the plan to a markdown file so it can be opened with rendered
mermaid — in an IDE preview (VS Code, Ctrl/Cmd+Shift+V) or on GitHub
(renders mermaid natively).
What to save
The current plan under discussion — typically the approved plan-mode plan (the harness plan file) or the most recent plan/design doc written in this session. Save it as-is when within its tier ceiling in references/doc-protocol.md; if over, trim to the plan template first and say what you cut. Keep mermaid blocks intact. If no plan exists yet, say so and stop — don't invent one.
Where it goes — artifact routing
This skill is for implementation plans (phased steps, to-do lists, acceptance
criteria). Docs are grouped by unit of work, not by type: one folder per feature,
bug fix, improvement, or enhancement at docs/work/<slug>/, holding everything
produced for it in per-type subfolders. The broader taxonomy:
| Artifact | Subfolder | Produced by |
|---|---|---|
| Implementation plan | plans/ |
This skill (default) |
| Architecture design / solution doc (no to-do list) | solutions/ |
@backend-architect, @frontend-architect directly |
| Architecture review report | architecture-reports/ |
@architect-reviewer directly |
| QA/regression verification report | qa-reports/ |
@qa-engineer directly |
| Per-change legal analysis | legal/ |
@saas-legal-advisor directly |
Layout, slug and collision: plugin conventions win — see rules/engineering-loop.md "Doc taxonomy".
For a pure architecture design, review report, or QA report, skip this skill —
the relevant agent writes directly to the correct subfolder inside
docs/work/<slug>/, following the same naming convention (create the folder + a
docs/work/README.md index row if missing).
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.
- 24d ago Changed · +5 lines 00c35538f406
- 1mo ago First seen · 80 lines · 83 tokens per session scan A 40865949d64a
save-plan is a skill published in the GitHub repository addit-digital/addit-harness (3 stars, last pushed 24d ago), licensed MIT. It adds 83 tokens to every session and 1,215 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 2026-08-31.
Other skills, from other repositories
memstack-business-scope-of-work
Use this skill when the user says 'scope of work', 'SOW', 'define scope', 'project scope', 'write SOW', 'scope document', or is defining project boundaries, deliverables, and acceptance criteria for a formal engagement. Do NOT use for proposals, contracts, or invoicing.
memstack-business-invoice-generator
Use this skill when the user says 'invoice', 'generate invoice', 'create invoice', 'bill client', 'line items', 'payment terms', or needs professional invoices with tax calculations and payment instructions. Do NOT use for contracts or financial projections.
java-spring-development
Java Spring Boot development guidelines with best practices for building robust, secure, and maintainable enterprise applications.
impact-report-writer
Nonprofit/NGO impact report generation with data visualization suggestions, outcome metrics, narrative structure, and program data presentation. Use when writing impact reports, annual reports, or program evaluation summaries.
investment-memo-generator
Investment memo creation combining financial analysis, document generation, and structured templates. Use when creating investment memos, pitch decks, deal summaries, or investment committee materials.
codebase-documenter
Write codebase documentation: READMEs, architecture docs, getting-started guides, API docs, and code comments. Use when documenting code or making a project easier for new developers.