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/devnomad-byte/techneering/agents-mdgit clone --depth 1 https://github.com/devnomad-byte/techneeringWhat 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 | $0.01174 | $0.01174 |
| Opus 5 | $0.00587 | $0.00587 |
| Sonnet 5 | $0.00235 | $0.00235 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
techneering 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 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Techneering
Open-source spec-driven skills plugin. Works on both Codex and Claude Code.
Plugin Identity
| Field | Value | Notes |
|---|---|---|
| Repository | github.com/devnomad-byte/techneering |
Open-source repo |
| Plugin name | tn |
Both Codex and Claude Code identifier |
| Skill call prefix | tn: |
Prefix for all skills (e.g. tn:compass) |
How Techneering Works With Codex
Codex reads this AGENTS.md before doing any work, and loads Techneering's skills from ./skills/. A SessionStart hook (in hooks/hooks.json, which Codex auto-discovers by default) also injects the tn:compass gateway at session start, mirroring the Claude Code experience. If the hook doesn't fire for any reason, the rules below still apply.
Why there's both AGENTS.md and CLAUDE.md (no conflict): Each host loads only its own file. Codex auto-loads AGENTS.md (this file); it does not auto-load CLAUDE.md. Claude Code auto-loads CLAUDE.md; it does not auto-load AGENTS.md. They serve the same purpose for two different hosts, so both ship in the repo. The hooks/hooks.json is shared — Codex injects CLAUDE_PLUGIN_ROOT for compatibility, so the one hook file works on both.
The single most important rule: Before responding to any user request, check whether a Techneering skill applies — and if it does, follow that skill. Start every session by consulting tn:compass to pick the right development path.
Skill Inventory
| Skill | Call | Type | Description |
|---|---|---|---|
| Compass | tn:compass |
Gateway | Auto-injected on session start, selects development path |
| Scout | tn:scout |
Flow | Standalone exploration mode, pure thinking, writes no files |
| Draft | tn:draft |
Flow | Generate proposal + specs + design + tasks |
| Forge | tn:forge |
Flow | Entry point: chains blueprint → assemble |
| Audit | tn:audit |
Flow | Dual-layer verification: spec compliance + requirement tracing |
| Vault | tn:vault |
Flow | delta merge → move into archive/ |
| Spark | tn:spark |
Process | Socratic questioning + project style detection + framework recommendation |
| Blueprint | tn:blueprint |
Process | Break into bite-sized tasks |
| Diagnose | tn:diagnose |
Rigid | 4 phases: root cause → pattern → hypothesis → fix |
| Gate | tn:gate |
Rigid | Iron law: run command → read output → claim → show menu |
| Redgreen | tn:redgreen |
Rigid | Red-green-refactor cycle |
| Assemble | tn:assemble |
Execution | Subagent dispatch + two-stage review + parallel scheduling |
| Inspect | tn:inspect |
Execution | Global cross-task review: consistency, architecture, security |
| Isolate | tn:isolate |
Execution | Create isolated workspace + verify test baseline |
| Ship | tn:ship |
Wrap-up | Branch integration: merge / PR / keep / discard |
| Craft | tn:craft |
Domain | Auto-stacked when a frontend task is detected |
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 · 79 lines · 1,174 tokens per session scan A b6d3e0c76fe8
techneering AGENTS.md is an instructions file published in the GitHub repository devnomad-byte/techneering (13 stars, last pushed 2mo ago), licensed MIT. It adds 1,174 tokens to every session, about $0.0059 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
pinfix AGENTS.md
AGENTS.md instructions for ForeverSc/pinfix, covering pinfix — agent knowledge base, what is pinfix, architecture, packages and key directories.
pinfix CLAUDE.md
Claude Code instructions for ForeverSc/pinfix, a project described as: 📌 Edit UI with Claude Code using on-page comments.
stackmemory CLAUDE.md
Claude Code instructions for stackmemoryai/stackmemory, covering croissant.ai — agent guide, stack, project structure, key files and detailed guides.
crystal CLAUDE.md
Instructions for stravu/crystal, covering crystal - multi-session claude code manager, project overview, references, implementation status: ✅ complete and ✅ implemented features.
easy-cheese python.instructions.md
Instructions for paulnsorensen/easy-cheese, covering hard rules, what to flag and what not to flag.
sandy CLAUDE.md
Instructions for jamestelfer/sandy, covering claude.md, voice, what is sandy, project layout and dev commands.