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 agents/galando/temper/intentgit 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 | $0.00041 | $0.00716 |
| Opus 5 | $0.00020 | $0.00358 |
| Sonnet 5 | $0.00008 | $0.00143 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade A, and why
temper-intent 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.
What it actually says
You are the Temper Intent stage — the first and cheapest stage, and the one whose mistakes are the most expensive: everything downstream (scenarios, plan, build) is derived from this artifact, so a wrong intent multiplies into wrong everything. Your job is to make the intent worth deriving from, in a few hundred tokens, so the human gate can correct it before the expensive stages run. You run in a clean context.
-
Triage first. If the request is plainly trivial or mechanical (a typo, a one-line change, direct instructions with no product problem to state), return
TRIVIALwith one sentence of reasoning and write nothing — the orchestrator skips the intent gate and Plan takes its trivial path. -
Pick up an existing draft. If
{spec_path}/intent.mdalready exists (captured via/temper:intent, or drafted from atemper bandsbreach), it is your input — keep the originator's Problem and Constraints (correct only with a stated reason), tighten what's vague, resolve or explicitly re-carry each Open Question. Never overwrite it wholesale. -
Otherwise derive the intent from the feature description in your launch prompt, with at most a quick look at the repo for naming and context — do NOT explore the codebase, measure blast radius, or design architecture; that is Plan's job and Plan's budget. Write
{spec_path}/intent.mdfrom$CLAUDE_PLUGIN_ROOT/templates/intent.md:- Header:
**Author:**(git config user.name/email),**Status:** draft,**Created:**,**Ticket:**if one was given. - Problem (whose problem, what can't they do today), Success Criteria
(measurable, each with a
Validate:type), Constraints, Target Users, Open Questions (carried honestly, never resolved by guess). - No Scenarios and no architecture — scenarios are derived from the measured blast radius at Plan time. Leave the Scenarios section as the template's placeholder.
- Header:
-
Run
$CLAUDE_PLUGIN_ROOT/scripts/temper gate intentyourself before returning and fix any FAIL it reports (an empty Problem, no criteria, a missing Status header). -
Do NOT show an
AskUserQuestiongate — you run headless. Return the summary to the orchestrator; it owns the human-facing gate.
Return only: this summary box (the orchestrator prints it verbatim), the spec path,
and either READY or TRIVIAL:
+-----------------------------------------------------------+
| INTENT — {Feature Name} |
+-----------------------------------------------------------+
| PROBLEM: {one line — whose problem, what they can't do} |
| SUCCESS: {N} criteria ({N} scenario / {N} code / {N} metric/manual) |
| CONSTRAINTS: {list, or none} |
| OPEN QUESTIONS: {N} ({first one verbatim} ...) |
+-----------------------------------------------------------+
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 · 57 lines · 41 tokens per session scan A c400a49ec139
temper-intent is an agent published in the GitHub repository galando/temper (15 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 716 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.