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 agents/crystian/skill-map/claude-agent-helpergit clone --depth 1 https://github.com/crystian/skill-mapWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/crystian/skill-map/claude-agent-helper)<a href="https://agentmods.dev/agents/crystian/skill-map/claude-agent-helper"><img src="https://agentmods.dev/badge/agents/crystian/skill-map/claude-agent-helper.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00019 | $0.00069 |
| Opus 5 | $0.00010 | $0.00034 |
| Sonnet 5 | $0.00004 | $0.00014 |
| Haiku 4.5 | $0.00002 | $0.00007 |
Grade A, and why
claude-agent-helper 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 4d 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
Claude-only agent
Under the opencode lens this is plain markdown, NOT an agent: OpenCode's
Claude-compatibility covers skills (and CLAUDE.md), not .claude/agents/.
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.
- 4d ago First seen · 10 lines · 19 tokens per session scan A efff8e161dd9
claude-agent-helper is an agent published in the GitHub repository crystian/skill-map (60 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 69 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 2026-08-30.
Other agents, from other repositories
chief-attribution
Produce progressive CHIEF failure attribution from validated candidates.
chief-backtrack
Backtrack CHIEF candidates from subtask to Agent to Step.
chief-graph
Build a hierarchical causal graph from a frozen multi-agent trajectory.
chief-oracle
Synthesize Virtual Oracle expectations for CHIEF subtasks.
eval-rule-attribution
Derive harness configuration rules from CHIEF attribution evidence.
eval-rule-merge
Semantically match new eval rules to an existing rule store.