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 matheusPavaneli/workbench --skill plan-changegit clone --depth 1 https://github.com/matheusPavaneli/workbenchWrote 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/matheuspavaneli/workbench/plan-change)<a href="https://agentmods.dev/skills/matheuspavaneli/workbench/plan-change"><img src="https://agentmods.dev/badge/skills/matheuspavaneli/workbench/plan-change/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/matheuspavaneli/workbench/plan-change"><img src="https://agentmods.dev/badge/skills/matheuspavaneli/workbench/plan-change.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 | $0.00043 | $0.01020 |
| Opus 5.5 | $0.00017 | $0.00408 |
| Sonnet 5.5 | $0.00009 | $0.00204 |
| Haiku 4.5 | $0.00004 | $0.00102 |
Grade A, and why
plan-change 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 1mo 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plan-change
wb <args> # wb not on PATH: python <this skill's directory>/../../lib/wb.py <args>
Steps
-
Load the ticket.
sdd getis not it — read.workflow/<KEY>/triage.json. No triage yet? Runtriage-taskfirst, or work from what the user stated and record that inquestions. -
Get the bar.
repo profile. It prints the preset, the repo's own conventions, and the gates that apply. Follow the conventions it reports; do not introduce a second test runner or package manager.LOW confidencemeans the preset is a guess nobody reviewed: say so, let the user settle it. Once the file list is known,repo gates <paths>resolves the bar those paths land in — in a monorepo that is not the repo's, and the audit fails a plan that declares a preset below it. -
Pick a persona from
references/personas.md. It shapes what counts as done, not the format.A change already on disk (a light-path ticket
finishmoved here) stays: plan around it, never revert it to plan from scratch. -
Confirm everything in the code. Assume nothing. Every claim about this codebase needs a
file:lineand the text of that line, because the audit in step 7 reopens each one. A claim you cannot cite is a question, not a fact — put it inquestions. Search with the strongest tool available and quote only lines you actually read:../../shared/code-search.md. -
Find the raised bar.
repo zones <path>...with every file you plan to touch. Billing, auth, user data, migrations and secrets are held to a higher standard whatever the preset says. -
Write
.workflow/<KEY>/sdd.json. Shape and required fields:references/sdd.md. -
Audit.
sdd audit <KEY>. It must pass. On failure, fix the plan — never the citation to match a wrong claim, and never proceed to implementation. Thensdd render <KEY>for the human-readable copy.The audit reports a tier. Give every
files[]entry alinesestimate (added plus removed); an entry without one makes the planstandard. An estimated total within the repo's bound (100 by default), no critical zone and no bug/support ticket qualifies aslight, which waivesstepsandproduct— nothing else.impl checkmeasures the real diff against the bound, so an estimate written low only moves the failure later. Do not aim for a tier: write the plan the change needs and let the audit compute it. Citations, the file list,verifyandrollbackare required at every tier.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed a950487c4d4d
- 1mo ago Changed · +6 lines bbd150765d65
- 2mo ago First seen · 75 lines · 43 tokens per session scan A 32f81154312e
plan-change is a skill published in the GitHub repository matheusPavaneli/workbench (1 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 1,020 once invoked, about $0.0002 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
dev-kit-setup
First-use bootstrap for the dev kit. Detects the team's issue tracker, discovers what it can via MCP/CLI, asks only what cannot be discovered, and persists the result to .claude/dev-kit.json in the consuming repo. Use when that file is missing, when the user asks to set up or reconfigure the kit, or when issue-fetch…
plan-backlog
Turn an idea or description (in any format) into a well-formed backlog — epics, user stories with acceptance criteria, sub-tasks — and create it in the team's tracker after approval. Elaborates progressively (guided, the default) or in one shot (--quick). Supports Jira, Linear, GitHub Issues, and Azure DevOps via…
before-you-claim
Seven questions answered with evidence at the moment a change is written, one for each defect class this repo's fault register keeps recording — a sentence claiming what the code does not do, a check that cannot fail, a fix for the instance while the class stays open, a rule that lives in prose with no mechanism, a…
create-pr
Create a branch, commit the work, and open a pull request for a completed user story, after all quality gates pass. Use when the user asks to open/create a PR or as the final step of the story workflow.
issue-fetch
Fetch a work item (summary, status, description, acceptance criteria, comments) from the team's issue tracker and display a clean summary. Supports Jira, Linear, GitHub Issues, and Azure DevOps via adapters. Use whenever a prompt contains an issue reference (e.g. PROJ-1234, ENG-42.
issue-update
Update the work item after delivery - comment the PR link and a product-facing summary, and transition it to the team's review status. Supports Jira, Linear, GitHub Issues, and Azure DevOps via adapters. Use right after a PR is created for a story, or when the user asks to update/move a ticket.