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 instructions/anvanster/tempera/claude-mdgit clone --depth 1 https://github.com/anvanster/temperaWrote 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/instructions/anvanster/tempera/claude-md)<a href="https://agentmods.dev/instructions/anvanster/tempera/claude-md"><img src="https://agentmods.dev/badge/instructions/anvanster/tempera/claude-md.svg" alt="Measured on agentmods" 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 | $0.00652 | $0.00652 |
| Opus 5 | $0.00326 | $0.00326 |
| Sonnet 5 | $0.00130 | $0.00130 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
tempera CLAUDE.md 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 3d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tempera
Persistent episodic memory system for AI coding assistants. Single Rust crate, two binaries.
Build & Test
./scripts/ci-checks.sh # clippy + fmt + tests
./scripts/ci-checks.sh --full # + benchmarks, docs, coverage
cargo test --workspace # tests only
cargo test -- <test_name> # specific test
cargo build --release # release build (LTO, slow)
Architecture
Single crate (src/) with two binaries:
tempera(CLI):src/main.rstempera-mcp(MCP server):src/mcp_server.rs
Key modules (functional grouping):
| Group | Modules |
|---|---|
| Core data | episode.rs, store.rs, indexer.rs, keyword.rs, fingerprint.rs |
| Capture + retrieve | capture.rs, retrieve.rs, utility.rs, llm.rs, config.rs |
| Diagnostics | stats.rs, feedback.rs, doctor.rs, eval.rs |
| Operations | jobs.rs, backup.rs |
| Dream cycle (v0.7) | dream.rs, triage.rs, reflect.rs, patterns.rs, contradict.rs |
| Self-improvement (v0.8) | calibration.rs, mistakes.rs, templates.rs, templates_phase.rs, asks.rs, ask_backs.rs, ask_back_gen.rs |
| Brief surface (v0.9) | brief.rs |
templates.rs / ask_backs.rs / templates_phase.rs / ask_back_gen.rs split: the lean store types are shared between both binaries, the LLM-bearing pipelines are only registered in the tempera (CLI) binary.
Error handling: anyhow::Result throughout, thiserror for typed errors.
MCP Tool Surface (12 tools)
- Read surfaces:
tempera_retrieve,tempera_status,tempera_stats,tempera_brief,tempera_session_start,tempera_template - Write surfaces:
tempera_capture,tempera_feedback,tempera_log_correction,tempera_log_should_have_asked - Maintenance:
tempera_propagate,tempera_review
tempera_brief(files, task_type?, domain?) is the recommended task-start call once the file set is known. tempera_session_start is the recommended call even earlier — before files are known.
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.
- 3d ago First seen · 47 lines · 652 tokens per session scan A 1bd72d0e5055
tempera CLAUDE.md is an instructions file published in the GitHub repository anvanster/tempera (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 652 tokens to every session, about $0.0033 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 2026-08-31.
Other instructions, from other repositories
cognirepo CLAUDE.md
Instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).
openexp CLAUDE.md
Instructions for anthroos/openexp, covering openexp — development instructions, memory protocol (mandatory), before starting any task, after completing a task and when the user shares context.