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/willwebster5/agent-skills/socgit clone --depth 1 https://github.com/willwebster5/agent-skillsWhat 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 | $0.00000 | $0.00365 |
| Opus 5 | $0.00000 | $0.00182 |
| Sonnet 5 | $0.00000 | $0.00073 |
| Haiku 4.5 | $0.00000 | $0.00036 |
Grade A, and why
soc 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 3d 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.
What it actually says
<rules priority="critical">
<rule>Always invoke the soc skill for processing</rule>
<rule>Never modify detection templates without explicit user approval</rule>
<rule>Update .claude/skills/soc/memory/ files after every triage session per the Living Documents protocol</rule>
<rule>Suggest environmental-context.md updates when new context is discovered during investigation</rule>
<rule>Follow the principle of least filtered — FP is always better than a missed TP</rule>
</rules>
<actions>
<action trigger="starts-with:triage">
Triage the alert. Follow the soc skill workflow.
</action>
<action trigger="starts-with:daily">
Review today's untriaged alerts. Follow the soc skill daily mode workflow.
</action>
<action trigger="starts-with:tune">
Tune the specified detection. Follow the soc skill tuning workflow.
</action>
<action trigger="starts-with:hunt">
Hunt for threats. Follow the soc skill hunt mode workflow.
</action>
<action trigger="default">
Show available subcommands:
/soc triage <alert-url-or-id> — Triage a specific alert (full lifecycle)
/soc daily [product] — Review today's untriaged alerts (product: endpoint, ngsiem, identity, cloud_security)
/soc tune <detection-name> — Tune a detection (skip triage)
/soc hunt <description-or-IOCs> — Threat hunting mode
</action>
</actions>
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.
- 3d ago First seen · 39 lines · 0 tokens per session scan A b58dc01a890c
soc is a command published in the GitHub repository willwebster5/agent-skills (12 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 365 tokens. 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 2026-08-30.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
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.