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/tene-ai/tene/copilot-instructionsgit clone --depth 1 https://github.com/tene-ai/teneWrote 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/tene-ai/tene/copilot-instructions)<a href="https://agentmods.dev/instructions/tene-ai/tene/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/tene-ai/tene/copilot-instructions.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 | $0.00608 | $0.00608 |
| Opus 5 | $0.00304 | $0.00304 |
| Sonnet 5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
tene copilot-instructions.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 4d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot — tene Project Instructions
This repository is tene, a local-first encrypted secret manager CLI. When suggesting code or commands for this project, follow these rules.
AI-Safe Secret Handling (critical)
- ALWAYS prefer
tene run -- <cmd>overtene get <KEY>when helping users run something that needs secrets.tene run --injects secrets as environment variables;tene getprints plaintext to stdout which enters the AI context window. - NEVER suggest
tene exportin code — it prints all secrets as plaintext. - NEVER suggest reading files under
.tene/— it is the encrypted vault. - NEVER pass secret values as command-line arguments (they appear in
psand shell history). Use environment injection viatene run --. tene listis safe — it shows secret names only, no values.tene get KEY --jsonreturns{"name":..., "value":..., "environment":...}and requires explicit--unsafe-stdoutorTENE_ALLOW_STDOUT_SECRETS=1on non-TTY invocation (default behavior blocks to prevent AI context leakage).
Project Conventions
- Language: Go 1.25+ (CLI) · TypeScript / Next.js 15 App Router
(landing at
apps/web/). - License: MIT.
- Commit messages: Conventional Commits (
feat(cli):,fix(vault):,docs(readme):,chore(deps):, ...). - Branches: feature branches off
staging, merged intostaging, released frommain(auto-tag workflow handles versioning). - Testing:
go test -race ./...+golangci-lint runmust pass before merge. - No network calls in the CLI default path — tene is local-first by design. Cloud features (disabled in v1.x) live behind a separate opt-in.
Do Not
- Do not add new third-party dependencies without discussing in an issue.
- Do not introduce hardcoded secrets in any example or test.
- Do not suggest
.envfiles — that is exactly the problem tene solves. - Do not suggest cloud-backed secret managers (Vault, AWS Secrets Manager,
Doppler) as alternatives within tene's code — link to
/vs/*comparisons on tene.sh instead.
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.
- 4d ago First seen · 53 lines · 608 tokens per session scan A 012693b2efc5
tene copilot-instructions.md is an instructions file published in the GitHub repository tene-ai/tene (15 stars, last pushed 2mo ago), licensed MIT. It adds 608 tokens to every session, about $0.0030 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
Pake AGENTS.md
AGENTS.md instructions for tw93/Pake, covering agents.md - pake project knowledge base, project identity, repository structure, development commands and code conventions.
codedb AGENTS.md
AGENTS.md instructions for justrach/codedb, covering codedb agent guidelines, what codedb is (and isn't), review guidelines, pre-merge verification and security-sensitive areas.
codedb copilot-instructions.md
Copilot instructions for justrach/codedb, covering codedb — agent instructions, project, rules, filing issues and test style.
codedb CLAUDE.md
Claude Code instructions for justrach/codedb, covering codedb — agent instructions, project, rules, filing issues and test style.
Pake copilot-instructions.md
Copilot instructions for tw93/Pake, a project described as: 🤱🏻 Turn any webpage into a desktop app with one command.
Pake CLAUDE.md
Claude Code instructions for tw93/Pake, a project described as: 🤱🏻 Turn any webpage into a desktop app with one command.