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/crypticswarm/swarmforge/commandgit clone --depth 1 https://github.com/CrypticSwarm/SwarmforgeWhat 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 | $0.00007 | $0.00471 |
| Opus 5 | $0.00003 | $0.00235 |
| Sonnet 5 | $0.00001 | $0.00094 |
| Haiku 4.5 | $0.00001 | $0.00047 |
Grade A, and why
command 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
Activate the general-software-engineering skill before taking any other action.
Command request: $ARGUMENTS
Expected arguments:
- Action:
create,update, orupsert - Optional scope:
globalorlocal(default:global) - Command name (kebab-case, without leading
/and without.md) - What the command should do (1–3 sentences)
If any of these are missing or ambiguous, ask follow-up questions and stop.
Current working tree:
!git status --short
Existing global commands (if present):
!ls commands 2>/dev/null || ls ~/.config/opencode/command 2>/dev/null || true
Existing local commands (if present):
!test -d .opencode/command && ls .opencode/command || true
Locate the target command prompt file based on scope:
- Global:
commands/<command-name>.mdwhen the workspace has a top-levelcommands/directory (the Swarmforge checkout), otherwise~/.config/opencode/command/<command-name>.md - Local:
.opencode/command/<command-name>.md(create the.opencode/command/directory if needed)
Behavior:
create: If the file already exists, ask whether toupdateit instead and stop.update: If the file does not exist, ask whether tocreateit (or confirm the correct name/scope) and stop.upsert: If the file exists, update it; otherwise, create it.
When creating a new command prompt file:
- Include YAML frontmatter with
description,agent, andmodel(no extra keys). - Prefer
agent: buildunless the command is purely advisory. - Keep the body short and deterministic: validate
$ARGUMENTS, then provide clear instructions. - Inject only small, high-signal
!context blocks (for example:git status --short,git diff,ls,rg).
When updating an existing command prompt file:
- Make minimal, focused edits consistent with the surrounding style.
- Preserve any useful context blocks unless they are clearly stale or noisy.
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 · 45 lines · 7 tokens per session scan A 6513d41715ec
command is a command published in the GitHub repository CrypticSwarm/Swarmforge (2 stars, last pushed 2d ago), licensed MIT. It adds 7 tokens to every session and 471 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.
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.