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/galando/temper/plangit clone --depth 1 https://github.com/galando/temperWhat 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 | $0.00008 | $0.00808 |
| Opus 5 | $0.00004 | $0.00404 |
| Sonnet 5 | $0.00002 | $0.00162 |
| Haiku 4.5 | $0.00001 | $0.00081 |
Grade A, and why
plan 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan a Feature
Goal: Transform feature request into implementation plan with impact analysis.
Feature: $ARGUMENTS
Execution
Full methodology: Read
$CLAUDE_PLUGIN_ROOT/reference/plan.md
Subprocess Mode
If $CLAUDE_PLUGIN_ROOT/scripts/temper config get stages.subprocess false returns
true, don't run the methodology inline (skip the reference read and Quick Reference
below). Launch the same isolated subprocess /temper uses — model from temper model plan, prompt: "Follow $CLAUDE_PLUGIN_ROOT/agents/plan.md exactly. Feature:
$ARGUMENTS. Spec path: .temper/specs/{feature-slug}. Standalone run — no orchestrated
Intent stage ran: author intent.md yourself per reference/plan.md's standalone case,
and pass --spec-path .temper/specs/{feature-slug} to every temper gate call." Print
the returned box verbatim, then run both gates + the approval AskUserQuestion per
Deterministic Gate below — the subprocess is headless and already recorded its
evidence; the human gate stays in this context either way.
Quick Reference
- Detect input (Jira/GitHub/description)
- Explore with your own tools (a nested Explore subagent is a judgment call for large repos, not a mandatory step)
- Research external docs if needed
- Assess complexity + risk (trivial/simple/medium/complex)
- Blast radius analysis, measured not estimated (consumers, contracts, security hot paths)
- Derive BDD scenarios from the blast radius (medium+ complexity) — before architecture
- Clarify if ambiguous (max 2-3 questions, informed by scenarios)
- Generate exactly
intent.md+tasks.md+plan.md— never a fourth file — to.temper/specs/{feature}/with file-to-scenario traceability - For Medium and Complex: generate mermaid diagram + ASCII art equivalent in plan.md (## Diagram section); render ASCII in terminal summary (not raw mermaid)
- Record
temper state set complexity <tier>, then run BOTH gates with an explicit spec path and fix any FAIL — see Deterministic Gate below:temper gate intent --spec-path .temper/specs/{feature-slug}(whenever intent.md exists — authored here or picked up as a draft) andtemper gate plan --spec-path .temper/specs/{feature-slug} - Present for approval with 4 options: Continue / Walkthrough / Change / Save
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 · 65 lines · 8 tokens per session scan A b77221ceba77
plan is a command published in the GitHub repository galando/temper (15 stars, last pushed 3d ago), licensed MIT. It adds 8 tokens to every session and 808 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 2026-08-30.
Other commands, from other repositories
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.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.