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/dcotelo/cprof/profilegit clone --depth 1 https://github.com/dcotelo/cprofWhat 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 | $0.00009 | $0.00321 |
| Opus 5 | $0.00005 | $0.00161 |
| Sonnet 5 | $0.00002 | $0.00064 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
profile 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
Arguments: $ARGUMENTS
Run the matching command and report its output verbatim. Do not offer to switch
the current session's account — credentials are fixed at process start, so a
switch requires relaunching claude.
- No arguments: run
${CLAUDE_PLUGIN_ROOT}/scripts/cprof status, then${CLAUDE_PLUGIN_ROOT}/scripts/cprof which, then${CLAUDE_PLUGIN_ROOT}/scripts/cprof list. Ifstatusandwhichname different profiles, say so: this session is signed in as the former while the directory expects the latter, and only a relaunch closes the gap. pin <name>: run${CLAUDE_PLUGIN_ROOT}/scripts/cprof pin <name>, then state that a relaunch is required for it to take effect.rule <path> <name>: run${CLAUDE_PLUGIN_ROOT}/scripts/cprof rule add <path> <name>.rules: run${CLAUDE_PLUGIN_ROOT}/scripts/cprof rules. Rules are listed longest-path-first, which is the order resolution consults them; a rule marked(unknown profile)never matches anything.doctor: run${CLAUDE_PLUGIN_ROOT}/scripts/cprof doctor.- Anything else: run
${CLAUDE_PLUGIN_ROOT}/scripts/cprof help.
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 · 26 lines · 9 tokens per session scan A d28e0ef5e8a0
profile is a command published in the GitHub repository dcotelo/cprof (4 stars, last pushed 4d ago), licensed MIT. It adds 9 tokens to every session and 321 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
ssh-keys
Manage SSH keys across hosts — generate, sync, list status, or delete.
pi-code-review
Adversarial code review via Codex — break confidence in changes, not validate them.
pi-fact-check
Fact-check content via Gemini search + Claude verification — cross-provider claim validation.
setup
Install the claude-pace statusline bundled with this plugin.
pi-askall
Ask both Codex and Gemini the same question — get three perspectives with Claude synthesis.
pi-ask-gemini
Ask Gemini a question — get Google's perspective alongside Claude's.