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/new-skillgit 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 | $0.00010 | $0.00419 |
| Opus 5 | $0.00005 | $0.00210 |
| Sonnet 5 | $0.00002 | $0.00084 |
| Haiku 4.5 | $0.00001 | $0.00042 |
Grade A, and why
new-skill 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 skill-writer skill before taking any other action.
New skill request: $ARGUMENTS
Expected arguments:
- Scope:
globalorlocal - Skill name (kebab-case directory name)
- What the skill 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 skills (if present):
!ls skills 2>/dev/null || ls ~/.config/opencode/skills 2>/dev/null || true
Existing local skills (if present):
!test -d .opencode/skills && ls .opencode/skills || true
Create the skill in the appropriate location:
- If scope is
global, write toskills/<skill-name>/SKILL.mdwhen the workspace has a top-levelskills/directory (the Swarmforge checkout), otherwise~/.config/opencode/skills/<skill-name>/SKILL.md. - If scope is
local, write to.opencode/skills/<skill-name>/SKILL.md.
Ensure SKILL.md frontmatter contains only name and description.
Use description as an activation CTA ("MUST be activated when…").
After the skill content is drafted, determine whether a slash command should also be created for it.
- If scope is
global, commands live incommands/when the workspace has that top-level directory (the Swarmforge checkout), otherwise~/.config/opencode/command/. - If scope is
local, commands live in.opencode/command/.
If creating a command, confirm the desired command name and argument shape, then create <command-name>.md that:
- activates the new skill first,
- validates
$ARGUMENTS(ask and stop if missing), and - injects only small, high-signal
!context blocks.
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 · 41 lines · 10 tokens per session scan A a0e79167706f
new-skill is a command published in the GitHub repository CrypticSwarm/Swarmforge (2 stars, last pushed 3d ago), licensed MIT. It adds 10 tokens to every session and 419 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.