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/tfutils/tfenv/bashgit clone --depth 1 https://github.com/tfutils/tfenvWhat 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 | $0.00939 | $0.00939 |
| Opus 5 | $0.00469 | $0.00469 |
| Sonnet 5 | $0.00188 | $0.00188 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
tfenv bash.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 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bash Coding Standards — tfenv
These standards apply to ALL bash scripts in the tfenv repository. Read this entire document BEFORE writing or modifying any bash code.
Mandatory Pre-Write Verification
Before writing ANY bash code, verify you understand these rules. Violations caught after writing waste time — get it right first.
Shell Setup
Every script in libexec/ contains its own boilerplate for resolving
TFENV_ROOT and sourcing helpers. This is intentional — each script
must be executable in isolation. Do NOT refactor this into a shared loader.
#!/usr/bin/env bash
set -uo pipefail;
- Shebang:
#!/usr/bin/env bash(exact format) - Strict mode:
set -uo pipefail;— NEVER useset -e - The project does NOT use shellcheck — this is a deliberate choice
Indentation and Formatting
- 2-space indentation throughout (no tabs)
- Terminate ALL statements with a semicolon (
;) where syntactically correct - Include vim modeline at end of new scripts:
# vim: set syntax=bash tabstop=2 softtabstop=2 shiftwidth=2 expandtab smarttab :
Variables
- ALL variable references use braces:
${variable}(never$variable) - Script-local variables use lowercase:
${version},${remote} - Environment variables use UPPERCASE:
${TFENV_ROOT},${TFENV_ARCH} - Always quote variable expansions:
"${variable}" - Quote entire strings containing variables:
"${dir}/file"NOT"${dir}"/file - Use
${var:-default}for optional variables (scripts run withset -u)
Quoting
- Single-quote strings unless variable expansion is needed
- Double-quote strings that contain variable expansion
- NEVER use unescaped
!inside double-quoted strings (bash history expansion)
Command Substitution
- Use
$(...)NOT backticks
Error Handling
- NEVER use
set -e— handle errors explicitly - Use the project's existing error patterns:
error_and_diefor fatal errors (available vialib/helpers.sh)- Inline
||pattern for simple cases:some_command || error_and_die "Failed to do thing";
- Note:
error_and_diedoes NOT exist in the test context — tests useerror_and_proceedinstead
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 · 103 lines · 939 tokens per session scan A c9a29f63457c
tfenv bash.instructions.md is an instructions file published in the GitHub repository tfutils/tfenv (4,966 stars, last pushed 2mo ago), licensed MIT. It adds 939 tokens to every session, about $0.0047 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
tfmcp CLAUDE.md
Instructions for nwiizo/tfmcp, covering claude.md, quick reference, quality checks (run before commits), project structure and key rules.
infra CLAUDE.md
Instructions for anthr76/infra, covering claude.md, repository overview, development environment, common commands and task automation.
mirage CLAUDE.md
Instructions for strukto-ai/mirage, covering claude.md, repo layout, typescript packages, python/typescript parity and module layout.
lade AGENTS.md
Instructions for zifeo/lade, covering agents.md, build & test, house rules, project layout and maintainer note.
claudebar CLAUDE.md
Instructions for mryll/claudebar, covering claude.md, tooling, non-obvious rules, hardening rules — the widget runs inside omarchy-shell and release.
ralph CLAUDE.md
Instructions for SantanderAI/ralph, covering ralph — instrucciones del proyecto and paridad bash ↔ powershell (importante).