dev-loop AGENTS.md

Project instructions for dev-llm-wiki, a knowledge base of development practices and edge cases designed for coding agents. They define its folders, page format, and rules for finding and updating entries.

In plain words
What is it for?
Use them when routing a development task to the right wiki pages, reading working guidance, or adding and maintaining knowledge entries.
Why use it?
They help agents load only the relevant guidance and keep the wiki’s structure consistent.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/choiyounggi/dev-loop/agents-md
Clone the repo
git clone --depth 1 https://github.com/choiyounggi/dev-loop

Made for: Codex, OpenCode.

Per session 3,138 This file is loaded in full into every session.
When invoked 3,138 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.03138 $0.03138
Opus 5 $0.01569 $0.01569
Sonnet 5 $0.00628 $0.00628
Haiku 4.5 $0.00314 $0.00314

Measured yesterday against content hash 4d11c66b6110, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-loop 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.

AGENTS.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dev-llm-wiki — Agent Schema

You are the maintainer and consumer of this wiki. This file is the schema: it defines how the wiki is structured, how you route into it, how you write pages, and how you keep it healthy. Follow it exactly. When this file and your habits disagree, this file wins.

What this wiki is

A case-routed knowledge base of development best practices and edge cases, written for LLM agents to load as working context. It is not documentation for humans to browse (humans are welcome, but every formatting rule below exists to make an agent's context precise and small).

Three layers (Karpathy LLM-wiki pattern):

Layer Path Mutability
Schema AGENTS.md (this file), templates/ Change only with repo owner approval
Wiki wiki/** , INDEX.md, log.md You create and update via the workflows below
Workflows skills/ Change only with repo owner approval

Directory layout

INDEX.md                     # root map: domain → when to route there
log.md                       # append-only chronological change log
wiki/<domain>/index.md       # domain map: category/page → when to load it
wiki/<domain>/<category>/<page>.md
templates/page.md            # canonical page template
skills/ingest|query|lint/    # the three operations

Routing protocol (how to consume)

Routing takes one of two inputs. Planning routes from the intent — the task you are about to do. Review routes from the diff — what the code in front of you actually does. Steps 1-6 are the same for both; the review entry then adds step 7.

  1. Read INDEX.md. Match your task to a domain by its "route here when" line.
    • Several domains match: route to the domain that owns the artifact you will change (SQL/schema → databases; application code → backend; a failing system → debugging). Reading a second domain's index to check is cheap and sanctioned; bulk-loading pages from both is not.
    • Best match is marked scaffold: it has no pages. Use the cross-pointers in its index if any, take the next matching seeded domain, and append a gap entry to log.md.
  2. Read that domain's wiki/<domain>/index.md. Select pages by their "load when" lines — these are the routing gate. Load only pages whose line matches your situation.
  3. After loading, the page's "When this applies" should confirm the match. If it contradicts your situation, drop the page and append a drift entry to log.md (index line and page trigger disagree — a lint defect), unless the page content demonstrably serves your case anyway, in which case keep it and still log the drift.
  4. Sanctioned extra hops: when a loaded page routes you onward via an inline [page-id] reference or a related: id, follow it — the citing directive is the trigger. This is how constraint/index pages compose.
  5. If no page matches anywhere, answer from general knowledge explicitly labeled not wiki-backed, and append a gap entry to log.md.
  6. Apply the page's directives:
    • If your situation hits a listed edge case, follow the edge-case row, not the general rule.
    • Within a Do/decision table, when several rows match, apply the most specific row (rows are ordered general → specific); when a general row and a precondition-bearing row both fit, take the one that preserves the stated invariant.
  7. Review entry — route from the diff, then compare the page sets. When your input is a change rather than a task, derive the match from what the diff does, not from what its plan said it would do:

Read the full file on GitHub · 243 lines

Changes

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.

  1. yesterday First seen · 243 lines · 3,138 tokens per session scan A 4d11c66b6110

Subscribe to this mod's changes

dev-loop AGENTS.md is an instructions file published in the GitHub repository choiyounggi/dev-loop (4 stars, last pushed 2d ago), licensed MIT. It adds 3,138 tokens to every session, about $0.0157 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.

Related

Other instructions, from other repositories

cartographer CLAUDE.md

Instructions for BeppeTemp/cartographer, covering agents.md — cartographer, commands, code map, code navigation and adding an mcp tool.

BeppeTemp/cartographer · 1,695 tokens

Alex_Skill_Mall severity-tagged-commits.instructions.md

Every commit touching brain artefacts (instructions / skills / prompts / agents / config / docs/ledgers / HANDOFF) must carry a severity tag in the commit subject: [typo | clarification | behaviour | constitutional]. [behaviour] and [constitutional] require an ACT pass before commit.

fabioc-aloha/Alex_Skill_Mall · 1,630 tokens

Alex_Skill_Mall falsifiability-deadlines.instructions.md

Every new or edited brain artefact (instruction / skill / prompt / agent) must declare a specific falsification deadline — a literal date, an observable event, or count+time bound — not 'after N passes' or 'when conditions warrant'.

fabioc-aloha/Alex_Skill_Mall · 1,167 tokens

Alex_Skill_Mall terminal-command-safety.instructions.md

Prevent terminal command failures from shell metacharacter interpretation, output capture issues, and hanging commands.

fabioc-aloha/Alex_Skill_Mall · 985 tokens

Alex_Skill_Mall copilot-instructions.md

Instructions for fabioc-aloha/Alex_Skill_Mall, covering alex plugin mall: identity, mission, what the mall is, duty stack and cardinal rules.

fabioc-aloha/Alex_Skill_Mall · 1,764 tokens

Alex_Skill_Mall act-pass.instructions.md

Run the 7-step ACT pass on medium and high stakes work — Materiality first, then Hypothesise, Alternatives, Disconfirmers, Audit-priors, Severity, Commit.

fabioc-aloha/Alex_Skill_Mall · 1,586 tokens