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 agentmods add commands/mdsakalu/agent-plugins/newgit clone --depth 1 https://github.com/mdsakalu/agent-pluginsWhat 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 | $0.00009 | $0.00708 |
| Opus 5 | $0.00005 | $0.00354 |
| Sonnet 5 | $0.00002 | $0.00142 |
| Haiku 4.5 | $0.00001 | $0.00071 |
Grade A, and why
new 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 2d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a new workspace for any onboarded repository.
Resolve the metarepo path by reading ~/.claude/workspace-config.json and expanding ~ to $HOME.
The user's request: $ARGUMENTS
Steps
- Read
~/.claude/workspace-config.jsonto get the metarepo path. Expand~to$HOME. - Parse the user's request for:
- Repo name — which onboarded repository (e.g.,
my-repo) - Workspace name — must match:
epic-<kebab>,spike-<kebab>, orpr-<number> - Purpose (optional) — short description of the workspace's goal
- Owner (optional) — defaults to the user
- Repo name — which onboarded repository (e.g.,
- Discover available repos by scanning
<metarepo>/repos/for directories with.repo.json. - If the repo is ambiguous or missing:
- List available repos and ask the user via
AskUserQuestion - If no repos are onboarded, suggest
/workspace:add-repo
- List available repos and ask the user via
- If the repo is not onboarded, suggest:
/workspace:add-repo <org/repo> - Validate the workspace name (must match
epic-*,spike-*, orpr-*pattern). - Run the creation script:
bash ${CLAUDE_PLUGIN_ROOT}/scripts/workspaces/new-workspace.sh <repo> <name> --type <type> --purpose "<purpose>" --owner "<owner>" - Show the output and the workspace path:
<metarepo>/repos/<repo>/<name>/ - Ask the user what to do next using
AskUserQuestion:- Stay here — don't cd, remain in the current directory
- cd (keep context) — invoke
/workspace:cd <repo>/<name>to switch while preserving the current conversation - cd (fresh session) — invoke
/workspace:cd <repo>/<name>to switch with a fresh Claude session (zmx respawn) If the user picks "cd (keep context)" or "cd (fresh session)", invoke theworkspace:cdskill with the appropriate workspace path. For "cd (fresh session)", pass--freshas an additional argument.
Important
- Always resolve metarepo from
~/.claude/workspace-config.json, never hardcode paths. - Workspace directories live under
<metarepo>/repos/<repo>/<name>/. - Notes live under
<metarepo>/notes/<repo>/<name>/(git-tracked). - The script creates JJ workspace, workspace.json, README.md, and symlinks.
- For
pr-*workspaces, the script auto-fetches PR branch info viagh pr view. - Infer type from name prefix:
epic-*→ epic,spike-*→ spike,pr-*→ pr.
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.
- 2d ago First seen · 45 lines · 9 tokens per session scan A db3748b71bc9
new is a command published in the GitHub repository mdsakalu/agent-plugins (4 stars, last pushed 2mo ago), licensed MIT. It adds 9 tokens to every session and 708 once invoked, about $0.0000 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.