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/joshidikshant/devsquad/capacitygit clone --depth 1 https://github.com/joshidikshant/devsquadWhat 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 | $0.00011 | $0.00555 |
| Opus 5 | $0.00005 | $0.00278 |
| Sonnet 5 | $0.00002 | $0.00111 |
| Haiku 4.5 | $0.00001 | $0.00056 |
Grade A, and why
capacity 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 yesterday.
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.
What it actually says
DevSquad Capacity Report
Report your current CLI usage so DevSquad can make intelligent delegation decisions.
Instructions
Use AskUserQuestion to collect the user's current usage percentages. Explain how to check each one:
Ask the user these questions using AskUserQuestion:
Question 1: Claude usage %
- Header: "Claude %"
- Tell the user: "Check Claude: run
/statusthen look at the 'Current session' percentage" - Options: "0-25%", "25-50%", "50-75%", "75-100%"
Question 2: Gemini usage %
- Header: "Gemini %"
- Tell the user: "Check Gemini: run
geminithen/stats, look at the primary model's 'Usage left' and subtract from 100" - Options: "0-25%", "25-50%", "50-75%", "75-100%"
Question 3: Codex 5hr usage %
- Header: "Codex 5hr"
- Tell the user: "Check Codex: run
codexthen/status, look at '5h limit' percentage left and subtract from 100" - Options: "0-25%", "25-50%", "50-75%", "75-100%"
Question 4: Codex weekly usage %
- Header: "Codex weekly"
- Tell the user: "From the same Codex
/status, look at 'Weekly limit' percentage left and subtract from 100" - Options: "0-25%", "25-50%", "50-75%", "75-100%"
After collecting answers, map the ranges to midpoint values:
- "0-25%" → 12
- "25-50%" → 37
- "50-75%" → 62
- "75-100%" → 87
If user provides exact numbers via "Other", use those directly.
Then save the capacity data:
source "${CLAUDE_PLUGIN_ROOT}/lib/state.sh"
source "${CLAUDE_PLUGIN_ROOT}/lib/usage.sh"
init_state_dir
save_capacity <claude_pct> <gemini_pct> <codex_5hr_pct> <codex_weekly_pct>
After saving, run the status command to show the updated report:
bash "${CLAUDE_PLUGIN_ROOT}/skills/devsquad-status/scripts/show-status.sh"
Display the result to the user with the delegation recommendation.
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.
- yesterday First seen · 61 lines · 11 tokens per session scan A 4766cf5f6875
capacity is a command published in the GitHub repository joshidikshant/devsquad (7 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 555 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 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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.