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/abhisekjha/pith/focusgit clone --depth 1 https://github.com/abhisekjha/pithWrote 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/commands/abhisekjha/pith/focus)<a href="https://agentmods.dev/commands/abhisekjha/pith/focus"><img src="https://agentmods.dev/badge/commands/abhisekjha/pith/focus.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 | $0.00016 | $0.00163 |
| Opus 5 | $0.00008 | $0.00081 |
| Sonnet 5 | $0.00003 | $0.00033 |
| Haiku 4.5 | $0.00002 | $0.00016 |
Grade A, and why
focus 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
Load only the sections of a file relevant to the current question.
File: $ARGUMENTS
The file path is passed via stdin in a single-quoted heredoc and read by focus.py from argv[1], so shell metacharacters in the path are treated as literal bytes:
python3 "${CLAUDE_PLUGIN_ROOT}/tools/focus.py" --stdin-path <<'PITH_EOF_7f3a9c2e'
$ARGUMENTS
PITH_EOF_7f3a9c2e
Show the relevant sections to the user. If no sections match, show the file structure overview.
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 · 20 lines · 16 tokens per session scan A 605374a7e9a4
focus is a command published in the GitHub repository abhisekjha/pith (98 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 163 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 commands, from other repositories
recent
Show DomainTome nodes updated most recently. Use after a session to see what the graph captured.
learn
Force claude-smart to extract learnings from this session now.
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.
init
Bootstrap project context (project.intent.md and project.glossary.json) from an existing codebase using deterministic scan + LLM synthesis + interactive editing. Use --harness to scaffold additional repo-level harness docs.
check
Is the context layer still true? 0-token staleness + broken-citation audit (no LLM, CI-friendly). Add --status for the fast hash-only subset.
save
Save the current session digest. Fans out across every writable memory tier per the house-map. Tier 0 always; Tier 1 if reachable; Tier 2 only if registered writable with auth. Each tier independent — failures degrade gracefully.