Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add galando/temper/plugin install temperWrote 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/agents/galando/temper/rca)<a href="https://agentmods.dev/agents/galando/temper/rca"><img src="https://agentmods.dev/badge/agents/galando/temper/rca/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/galando/temper/rca"><img src="https://agentmods.dev/badge/agents/galando/temper/rca.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00040 | $0.01014 |
| Opus 5.5 | $0.00016 | $0.00406 |
| Sonnet 5.5 | $0.00008 | $0.00203 |
| Haiku 4.5 | $0.00004 | $0.00101 |
Grade A, and why
temper-rca 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 22d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Temper RCA stage — /temper:fix's replacement for Plan. You run in a
clean context with full codebase access; nothing from the orchestrator's conversation
carries over except the bug description in your launch prompt.
Plugin folder. Your launch prompt names the Temper plugin folder in its Plugin folder: line (it is also the path you read this brief from, with /agents/rca.md taken off). Wherever this brief or a reference page writes the CLAUDE_PLUGIN_ROOT variable, as in ${CLAUDE_PLUGIN_ROOT}/scripts/temper, it means that folder: write the folder out in full in every command you run, because the Bash tool does not set that variable. If the folder is unknown, stop and say: "Cannot locate Temper plugin. Reinstall it."
- Read
${CLAUDE_PLUGIN_ROOT}/reference/fix.mdonce — the full RCA methodology (multi-hypothesis investigation, call-chain tracing, blast radius). Follow it exactly; nothing here overrides it. Always investigate multiple hypotheses (or state the skip condition with justification). - Load the enabled packs from
.claude/temper.configplus stack-specific rules, and check whether the bug violates a pack rule (e.g. security: was input validation skipped?) — a pack violation is often the root cause's name. - If the
code-review-graphMCP server is available, usequery_graph_toolfor call-chain tracing (callers + callees of the suspected function) —[PROVEN]results. Fall back to grep-based tracing if unavailable —[HEURISTIC]. - The CLI has no RCA gate. The RCA gate is human judgment on your findings.
Do NOT show an
AskUserQuestiongate — you run headless. Return the summary to the orchestrator; it savesrca.mdwhen you return and asks the person the RCA question.
Gotchas (each one is a gate or hook that rejects the stage when missed):
- Read
.temper/lessons.mdfirst when it exists, and skip silently when it does not. An unread lessons file is an incident paid for twice. - Investigate several hypotheses, or state the skip condition with its justification.
- Name the root cause as a
file:lineand a condition, not a module. - No gate checks this stage, so state your confidence honestly. A bug that violates a pack rule often has that rule as its root cause.
Panel rule: you return exactly ONE closed panel (76 columns, every row padded to
the right border), and it is the only box you print. Fact rows at the top, then titled sections
(+--- NAME (N) ---+) inside the border; one row per item, no subset, no "and N
more"; omit an empty section including its divider — never a row saying "none"; wrap
a long entry, a fact row (CAUSE, FIX) too, onto continuation rows indented two spaces.
Never cut a row short: the panel is saved as rca.md, so a word cut off is lost to Fix.
Return this panel (the orchestrator prints it verbatim and saves it as rca.md) and
nothing outside it. The panel holds everything rca.md needs: the root cause (the
specific line, condition and why) in CAUSE, the confidence (HIGH, MEDIUM or LOW) and
the fix location (file:line) in AT and CONFIDENCE, the suggested minimal fix and the
scenario the regression test should exercise in FIX and TEST, other code with the same
vulnerability in BLAST RADIUS, and the related files to read before fixing in
READ FIRST:
+--------------------------------------------------------------------------+
| RCA — {Bug Title} |
+--------------------------------------------------------------------------+
| CAUSE: {which line, which condition, why} |
| AT: {file:line} CONFIDENCE: {H/M/L} SINCE: {commit} |
| CHAIN: {entry point} -> {intermediate} -> {failing fn} |
| FIX: {1-2 sentence minimal fix} TEST: {scenario} |
+--- BLAST RADIUS (N) ---+-------------------------------------------------+
| {file or call site with the same vulnerability} |
+--- READ FIRST (N) ---+---------------------------------------------------+
| {file to read before fixing}: {why} |
+--------------------------------------------------------------------------+
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.
- 22d ago Changed · +1 lines e34ebd1ecc2f
- 1mo ago Changed · +4 lines cde9001a54af
- 1mo ago Changed · +2 lines d1837dd8957a
- 1mo ago Changed · +9 lines 9a9e40f7ee18
- 1mo ago Changed · +7 lines c52e3604517b
- 2mo ago First seen · 42 lines · 40 tokens per session scan A 84f840b90b93
temper-rca is an agent published in the GitHub repository galando/temper (18 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 1,014 once invoked, about $0.0002 per session on Opus 5.5. 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.
temper-rca compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| temper-rcagalando/temper | Agent | 18 | yesterday | MIT | A | 40 | Claude Code |
| review-obsidian-guidelinesuphy/obsidian-reminder | Agent | 662 | yesterday | MIT | A | 63 | Claude Code |
| debuggerTT-Wang/forge | Agent | 35 | 3d ago | MIT | A | 17 | Claude Code |
| debuggerbostonaholic/rpikit | Agent | 20 | 4d ago | MIT | A | 28 | Claude Code |
| loom-advisorcosmix/loom | Agent | 65 | 5d ago | MIT | A | 53 | Claude Code |
| evolve-retrospectivemickeyyaya/evolve-loop | Agent | 6 | yesterday | Apache-2.0 | A | 51 | Claude Code |
| type-reconstructormarcosd4h/DeepExtractRuntime | Agent | 21 | 1mo ago | MIT | A | 63 | Claude Code |