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/nullhack/temple8/agents-mdgit clone --depth 1 https://github.com/nullhack/temple8What 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 | $0.02589 | $0.02589 |
| Opus 5 | $0.01295 | $0.01295 |
| Sonnet 5 | $0.00518 | $0.00518 |
| Haiku 4.5 | $0.00259 | $0.00259 |
Grade A, and why
temple8 AGENTS.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 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
A Python project with the staged-contract workflow wired in (flow set, agents/skills/knowledge, CI, tooling). Drive the pipeline one state at a time through flowr.
Binding constraints
- flowr is the single router. Every state change runs through flowr — no improvised routing, no skipping, no pre-empting a later state's work. One state's work is exactly its
output artifacts; the next begins only when the orchestrator transitions. - The orchestrator dispatches; the dispatched agent does the work. The orchestrator MUST invoke the state's
dispatch_toagent — it never authors the work. The handoff gives the agent:skillspaths,input artifacts,output artifacts(write only here), and the evidence keys to assert. The agent produces the artifacts and asserts evidence; it does not transition. - The state's contract is binding. Read every
input artifactbefore starting — missing means stop, not assume. Write only tooutput artifacts. - Assert only verified evidence; CI is the backstop. On a guarded transition flowr fires only on the dispatched agent's asserted evidence (
--evidence k=v); assert nothing you did not check — CI catches the lie (ruff/pyright/mypy.stubtest/pytest). Unguarded transitions (discovery, explore) carry no flowr gate — the orchestrator verifies the output artifacts and the stakeholder's approval IS the gate. - Branch discipline. Match the state's
git branch: discovery/explore/plan/deliver run ondev; build runs onfeature/<session_id>, cut from dev at build entry. The contract surface is committed todevat plan; the feature branch carries only the source implementation. Squash-mergefeature/<session_id>→devonly under the whole-suite gates, then delete the branch. No dangling branches. - Every requirement traced. Each interview finding maps to a test or an explicit deferral; an untraced requirement is a gap the simulate gate rejects.
- Only the orchestrator transitions. Producing artifacts is not finishing — the orchestrator's verified
flowr transitionis. A dispatched agent never runsflowr transition/flowr session, never assumes the next state, never declares the flow done. - Todo-first. The first action on entering a state is to create its one-state todo (the loop below). No todo = no work. Only the orchestrator holds the todo; regenerate it after every transition.
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 · 153 lines · 2,589 tokens per session scan A 5cd812fdd3b3
temple8 AGENTS.md is an instructions file published in the GitHub repository nullhack/temple8 (11 stars, last pushed 27d ago), licensed MIT. It adds 2,589 tokens to every session, about $0.0129 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 instructions, from other repositories
uv AGENTS.md
AGENTS.md instructions for astral-sh/uv, a project described as: An extremely fast Python package and project manager, written in Rust.
python-blueprint AGENTS.md
Instructions for johnthagen/python-blueprint, covering repository guidelines and general instructions.
clawrium AGENTS.md
Instructions for ric03uec/clawrium, covering clawrium, how it works, why, who is this for and quickstart.
uv CLAUDE.md
Claude Code instructions for astral-sh/uv, a project described as: An extremely fast Python package and project manager, written in Rust.
uv-python-repo-template AGENTS.md
Instructions for jarlor/uv-python-repo-template, covering agent guide, first read, default workflow, quality bar and template rules.
appkit-bpmn-server python.instructions.md
Python development guidelines and best practices for the appkit project.