Borrowing it
Nothing to install: this file belongs to hs737/mcp-server-for-ynab. 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/hs737/mcp-server-for-ynab/master/.agents/skills/local-workflow-reproducibility/SKILL.mdgit clone --depth 1 https://github.com/hs737/mcp-server-for-ynabWrote 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/hs737/mcp-server-for-ynab/local-workflow-reproducibility)<a href="https://agentmods.dev/skills/hs737/mcp-server-for-ynab/local-workflow-reproducibility"><img src="https://agentmods.dev/badge/skills/hs737/mcp-server-for-ynab/local-workflow-reproducibility/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/hs737/mcp-server-for-ynab/local-workflow-reproducibility"><img src="https://agentmods.dev/badge/skills/hs737/mcp-server-for-ynab/local-workflow-reproducibility.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 | $0.00028 | $0.00529 |
| Opus 5 | $0.00014 | $0.00264 |
| Sonnet 5 | $0.00006 | $0.00106 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
local-workflow-reproducibility 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 9d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local Workflow Reproducibility
Use this skill when local development or manual testing depends on repeated setup, seed, reset, fixture, or scenario-loading steps.
Use When
- local setup is repetitive or error-prone
- realistic test state requires many manual steps
- developers are copying IDs, tokens, or env values between tools
- manual testing depends on exact ordering
- seed or reset flows need guardrails
Read First
AGENTS.md(if present)README.mdandpyproject.toml(scripts, optional groups, entry points)Makefileorscripts/if present- Environment docs (for example
docs/environment.md,.env.example) - Existing fixtures under
tests/,scripts/, ortools/
Core Rules
- Repeated workflows should become scripts or documented commands, not tribal knowledge.
- Destructive reset flows should be explicit and guarded (confirm DB name, env file, or
--dry-runwhere appropriate). - Scenario data should be intentional and named.
- Local workflows should prefer exercising real app code paths where practical (run the MCP server, call tools via inspector/CLI).
- Docs should explain how to reset, seed, and test locally—including required env vars (for example YNAB API tokens) without committing secrets.
- Use a virtual environment (
uv,venv,poetry) consistently; document the canonical install and run commands.
Workflow
- Identify repeated manual setup pain.
- Decide whether it needs reset, load, list, or verify commands.
- Script the workflow with safety checks (Python CLI,
maketargets, or shell wrappers that callpython -m ...). - Document the command surface and expected state.
- Add or update
pytestfixtures or seed data as the model evolves.
Common Failure Modes
- manual setup requires many fragile steps
- resets can accidentally target the wrong environment
- scenarios drift from current schema or tool contracts
- docs list workflows that no longer work
- secrets committed or assumed in docs
- “works on my machine” without pinned deps in
pyproject.toml/ lockfile
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.
- 9d ago First seen · 55 lines · 28 tokens per session scan A 0db47b01d404
local-workflow-reproducibility is a skill published in the GitHub repository hs737/mcp-server-for-ynab (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 28 tokens to every session and 529 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
harness-design-fuzzing
Reference vocabulary for designing instrumented harnesses that drive vulnerability discovery — design classes (trigger-driven vs coverage-driven), tiered scope (T1 isolated function / T2 multi-component / T3 full build), systematic input exploration, the two-coverage distinction (fuzzer-feedback vs audit)…
gmail-query-syntax
Reference for Gmail's search query syntax — operators like is:sent, newerthan:, from:, has:attachment, label:, and how they compose. Read this when constructing a Gmail search query string for the googleworkspace.gmailsearchmessages Code Mode call, especially when filtering by sent vs received, recency, sender, or…
email-formatting
Markdown formatting conventions for email summary documents — heading depth, list style, line length, emoji policy, and a mandatory provenance footer. Read this when producing a markdown report that summarizes one or more email messages so the output matches the project's house style.
json-schema-emails
Canonical shape of the .workflow/emails/emails.json file passed between the fetch and summarize states — required fields (sender, recipient, subject, date, body), types, and field semantics. Read this whenever you write or read emails.json so producer and consumer agree on the shape.
summary-style-guide
Tone and length conventions for email summaries — voice, verb tense, what to include vs omit, and target sentence count. Read this when writing the prose Summary line for each email so the voice is consistent across the report.
llm-as-judge-evaluation
Evaluate LLM outputs using frontier models as judges. Use for pairwise model comparison, quality scoring with custom rubrics, and automated evaluation pipelines. Covers position bias mitigation, statistical significance, and generating preference data for DPO/RLHF.