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/fprochazka/claude-code-plugins/brief-next-stepsgit clone --depth 1 https://github.com/fprochazka/claude-code-pluginsWhat 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 | $0.00027 | $0.00772 |
| Opus 5 | $0.00014 | $0.00386 |
| Sonnet 5 | $0.00005 | $0.00154 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
brief-next-steps 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brief Next Steps
Compress what this session landed on into one short file the user can read in ten minutes and act on. The output is the final proposal in implementation order — the conclusion, not the argument.
Scope
$ARGUMENTS
If empty, brief the whole session. If the session covered several unrelated threads, brief the one being worked on and note the omission in one line.
Sources
You (the orchestrator) write the file yourself — never a subagent, because the primary source is the conversation you are holding. Priority order: (1) the session itself — this is often the only source, and that is the normal case; (2) ./.claude/plans/*.md if any exist — newest proposal primary, older files for specific facts only; (3) docs/tickets already read this session — anchor, do not re-read. Never go exploring for new material — a missing fact goes in the "not yet verified" section, not into a research round.
Output path
Worktree-local ./.claude/plans/<slug>-briefing.md (mkdir -p; never /tmp, scratchpad, or docs/). Slug: $ARGUMENTS, else ticket ID (lowercase), else kebab-case topic. If the file exists, overwrite it wholesale — a briefing is a snapshot of current state; do not patch, do not suffix -2.
The briefing
As short as the material allows, hard ceiling ~170 lines, no floor — padding is a failure. Structure:
- Two or three sentences of context at the top. No further preamble.
- If two terms were actually being confused, one short section separating them.
- Steps in implementation order. Each heading names the problem in plain language, not the mechanism ("The quantities we ordered are never refreshed on the mirror", not "Add a refresh job"). Within each: what is wrong → what we change and which parts we touch → what that gets us → what it unlocks next. Each step ships on its own; if two are independent, say so in one line instead of inventing a dependency.
- Closing section: decisions the user still owes — one line each, ending in an actual choice, pointing at its step. Mandatory — this is the point of the file; dropping the unblocking decisions is the failure mode in the other direction.
- Second closing section: not yet verified — one line each, no elaboration.
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 · 50 lines · 27 tokens per session scan A 6cc2326d3e22
brief-next-steps is a command published in the GitHub repository fprochazka/claude-code-plugins (11 stars, last pushed 4d ago), licensed MIT. It adds 27 tokens to every session and 772 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
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.
constitution
Create or update the project constitution from interactive or provided principle inputs.