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/benkapner/claude-code-basecamp/focusgit clone --depth 1 https://github.com/Benkapner/claude-code-basecampWhat 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 | $0.00023 | $0.00673 |
| Opus 5 | $0.00012 | $0.00336 |
| Sonnet 5 | $0.00005 | $0.00135 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
focus scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Focus Command
Switch repository focus mid-session.
Instructions
Step 1: Scan Available Repositories
# List all git repos in repositories/
for dir in repositories/*/; do
if [ -d "$dir/.git" ]; then
name=$(basename "$dir")
branch=$(git -C "$dir" rev-parse --abbrev-ref HEAD 2>/dev/null || echo "unknown")
status=$(git -C "$dir" status --porcelain 2>/dev/null)
if [ -n "$status" ]; then
count=$(echo "$status" | wc -l | tr -d ' ')
hint="$branch, $count uncommitted"
else
hint="$branch, clean"
fi
printf " %s. %-30s (%s)\n" "$i" "$name" "$hint"
fi
done
Step 2: Present the Menu
Show the numbered list:
REPOSITORY FOCUS
================
1. my-project (main, clean)
2. backend-api (feature/add-retry, 3 uncommitted)
3. frontend-app (main, clean)
Which repo(s)? (e.g. 1, 1-3, all, all except 2)
If there is a current focus, mark it:
2. backend-api (feature/add-retry, 3 uncommitted) [current]
Step 3: Apply Selection
The user's response completely replaces the previous focus. Parse their selection:
2→ single repo1 3→ multiple repos by number1-3→ rangeall→ all reposall except 2→ all minus specific ones- Repo names also work:
backend-api
Step 4: Confirm
Focused on: backend-api, frontend-app
Then continue working. Apply the same focus constraint: only read/modify files in the selected repo(s) unless the user explicitly asks otherwise.
Step 5: Update tmux Window Name
If running inside tmux, rename the current window to reflect the focused repo(s):
# Only if inside a tmux session
if [ -n "$TMUX" ]; then
# Single repo: use repo name
# Multiple repos: "first-repo+N" where N is the count of additional repos
tmux rename-window "WINDOW_NAME"
fi
Examples:
- 1 repo selected →
tmux rename-window "backend-api" - 3 repos selected →
tmux rename-window "backend-api+2"
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.
- 2d ago First seen · 94 lines · 23 tokens per session scan A aa398f559458
focus is a command published in the GitHub repository Benkapner/claude-code-basecamp (16 stars, last pushed 12d ago), licensed MIT. It adds 23 tokens to every session and 673 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
spec-forge
Use when generating software specifications — full chain (Idea→Decompose→Tech Design + Feature Specs) or individual documents.
propagate
Use after editing an upstream doc (PRD/SRS/tech-design/feature-spec) to propagate changes downstream and keep the entire doc chain consistent.
analyze
Use when analyzing a document collection to map themes, find conflicts, gaps, and redundancies — generates landscape analysis report.
audit
Use when auditing existing project docs for quality, completeness, and code alignment — generates findings report with fix recommendations.
review
Use when reviewing spec-forge generated documents for quality, completeness, and consistency — auto-fixes issues if found.
tech-design
Use when writing a tech design, architecture doc, RFC, or design document — follows Google Design Doc format.