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 atretyak1985/swarmery --skill workspace-plansgit clone --depth 1 https://github.com/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/workspace-plans)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/workspace-plans"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/workspace-plans/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/atretyak1985/swarmery/workspace-plans"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/workspace-plans.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 | $0.00054 | $0.01421 |
| Opus 5.5 | $0.00022 | $0.00568 |
| Sonnet 5.5 | $0.00011 | $0.00284 |
| Haiku 4.5 | $0.00005 | $0.00142 |
Grade A, and why
workspace-plans 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 today.
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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
The private workspace plan format is a contract: the control plane parses it to render plan progress, phase summaries, and spec coverage. A plan that deviates from the format ships work the operator cannot see.
The contract (never violate)
- Plans live at
<workspace>/<project>/workspace/working/{YYYY}/{MM}/{DD}/{slug}/plan/; task-idyyyy-mm-dd-slugis derived from the path — never encode the date in the folder name. plan/README.md— objective, architecture decisions with real file paths, the sequencing table with exactly these header cells:| # | Phase | Doc | Depends on |, risks, Definition of Done.plan/phase-N-<slug>.mdper phase (flat;step-NN-*.mdis legacy read-compat only) — each with a self-contained copy-paste executor prompt whose Verify block is file-backed (a repo script or test by absolute path; no heredoc,python3 -ornode -e— seeresources/plan-format.md),- [ ]acceptance criteria checkable by command or boolean inspection, and an empty## Completion Reportsection as the LAST section.- A
## Forecastsection in each phase doc, immediately before that stub, holding onekind: prioryaml block (seeresources/plan-format.md). It is a prediction, not a limit: do whatever the phase actually needs. plan/manifest.json— machine-readable phase DAG (must passpython3 -m json.tool).- Optional
plan/spec.mdwith- [ ] **SC-n** — <criterion>lines; then every phase doc carries a**Covers:** SC-…header line (coverage is linted).
Criteria closed by a push, PR or merge start with [LAND]; criteria only a
human can perform (production, a console, a manual check) start with
[MANUAL]. Neither is the executor's to tick or perform: the daemon settles a
run against the rest, refuses to start a [MANUAL]-only phase, lists it in
Needs you, and ticks [LAND] itself only for a phase landed through the
Review tab. The header rows **Verify:** (off | normal | strict) and
**Review:** (on | off) sit directly after **Repo:** …; L/XL phases default
to normal / on. Details: resources/plan-format.md → "Criterion classes"
and "Header rows".
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.
- today Changed · +15 lines 7061ae7484d1
- 9d ago Changed · +11 lines 541456c3cf39
- 25d ago Changed · +9 lines 680e5eb61210
- 1mo ago Changed · +4 lines 3a4df08bcd7d
- 1mo ago Changed · +2 lines a96796586304
- 1mo ago First seen · 65 lines · 54 tokens per session scan A 2b93d45c8903
workspace-plans is a skill published in the GitHub repository atretyak1985/swarmery (7 stars, last pushed today), licensed Apache-2.0. It adds 54 tokens to every session and 1,421 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 2026-09-03.
Other skills, from other repositories
execute
Execute phase — wave-based crew dispatch with critic gates and evidence-based verification.
recipe-batch-invite-to-event
Add a list of attendees to an existing Google Calendar event and send notifications.
recipe-block-focus-time
Create recurring focus time blocks on Google Calendar to protect deep work hours.
recipe-create-shared-drive
Create a Google Shared Drive and add members with appropriate roles.
recipe-find-free-time
Query Google Calendar free/busy status for multiple users to find a meeting slot.
recipe-organize-drive-folder
Create a Google Drive folder structure and move files into the right locations.