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/fixgit 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 | $0.00006 | $0.01821 |
| Opus 5 | $0.00003 | $0.00911 |
| Sonnet 5 | $0.00001 | $0.00364 |
| Haiku 4.5 | $0.00001 | $0.00182 |
Grade A, and why
fix 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix: RCA → Fix → Review → Check
Goal: Investigate root cause, implement minimal fix, then review and check —
the same full pipeline as /temper, with RCA replacing Plan and Fix replacing Build.
Usage
/temper:fix "users get 500 error on checkout" # Start new fix
/temper:fix "JIRA-123" # Fix from Jira ticket
/temper:fix "#456" # Fix from GitHub issue
/temper:fix # Resume saved fix
Architecture
Each stage runs in an isolated Agent subprocess — genuine context clearing, not
theater. What each stage must do lives in exactly one place: agents/{stage}.md
(frontmatter declares its default model; the body carries methodology pointers, the
temper commands to run, and the summary box it returns). This file does not repeat
that contract per stage — read the agent file once when you launch it, and print the
box the agent returns verbatim.
ORCHESTRATOR (this file)
|
+-- Agent(agents/rca.md) -> RCA gate (human judgment — no CLI gate)
+-- Agent(agents/fix.md) -> fix gate -> temper gate build
+-- Agent(agents/review.md) -> review gate -> temper gate review
+-- Agent(agents/check.md) -> check gate -> temper gate check
|
+-- temper gate commit -> commit
Shared patterns: read $CLAUDE_PLUGIN_ROOT/reference/orchestrator-patterns.md once,
now — every → pattern reference below points into it. $CLAUDE_PLUGIN_ROOT
resolution is defined there; $TEMPER below means $CLAUDE_PLUGIN_ROOT/scripts/temper.
Why this command gates at all: the commit hook (scripts/hooks/install.sh) runs
temper gate commit on every git commit, regardless of which command produced it.
Fix maps onto the build gate (a regression test is exactly a RED-then-GREEN pair);
Review and Check are the literal same stages as /temper, sharing agents/review.md /
agents/check.md. Skipping evidence here would leave every /temper:fix commit
wrongly blocked (missing evidence fails closed, by design).
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 · 175 lines · 6 tokens per session scan A a87f8ca19a80
fix is a command published in the GitHub repository galando/temper (15 stars, last pushed 3d ago), licensed MIT. It adds 6 tokens to every session and 1,821 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.