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/amohamma8029/devlog/agents-mdgit clone --depth 1 https://github.com/amohamma8029/devlogWhat 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 | $0.01216 | $0.01216 |
| Opus 5 | $0.00608 | $0.00608 |
| Sonnet 5 | $0.00243 | $0.00243 |
| Haiku 4.5 | $0.00122 | $0.00122 |
Grade A, and why
devlog 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — devlog
Reference for AI agents and human contributors working in this repo.
REPO FACTS (3–5 lines)
What this is, who uses it, one key constraint or rule a new contributor needs first.
A CLI/TUI tool that records structured coding session journals inside a git repo. Used by solo developers or async coding partners (human or AI) to capture context, blockers, and handoffs. One global devlog per repo. Never auto-commits.
COMMANDS (put these first — agents reference them constantly)
mise install # install pinned Go version (if using mise) go build -o devlog.exe ./cmd/devlog # compile go test ./... # run after EVERY change; stop on first failure go test ./... -v # verbose output for debugging
Stack
Go 1.22+, Cobra (CLI), Bubble Tea + Bubbles + Lipgloss + Glamour (TUI). Storage: YAML front-matter + Markdown body, one file per session in .devlog/sessions/.
PROJECT STRUCTURE
cmd/devlog/ — CLI entrypoint (main.go + Cobra command wiring) internal/session/ — Session lifecycle (start, stop, list, find active) internal/store/ — File I/O for .devlog/sessions/*.md (YAML front-matter + Markdown body) internal/handoff/ — Summary artifact generation from session data internal/git/ — Repo root detection, branch name, author identity from git config internal/tui/ — Bubble Tea interactive interface internal/skill/ — Agent skill installation (embeds SKILL.md, writes to tool skill directories)
CODE STYLE
Conventions — concrete rules beat vague descriptions
- Return explicit errors; never swallow them with blank identifiers
- One session = one file in .devlog/sessions/; append-only during a session
- Never auto-commit or stage git changes; the tool writes files only
- Author identity from git config user.name/email; env fallback DEVLOG_AUTHOR_NAME / DEVLOG_AUTHOR_EMAIL
- Go standard naming: PascalCase exported, camelCase unexported
- No runtime dependencies added without asking first
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 · 114 lines · 1,216 tokens per session scan A a17502e6e229
devlog AGENTS.md is an instructions file published in the GitHub repository amohamma8029/devlog (2 stars, last pushed 14d ago), licensed MIT. It adds 1,216 tokens to every session, about $0.0061 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.
Other instructions, from other repositories
no-mistakes AGENTS.md
AGENTS.md instructions for kunchenguid/no-mistakes, covering agents.md and maintaining this file.
trpc-agent-go AGENTS.md
AGENTS.md instructions for trpc-group/trpc-agent-go, covering agents.md, project overview, engineering principles, go design conventions and implementation workflow.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.
goai AGENTS.md
Instructions for zendev-sh/goai, covering agents.md - goai, commands, architecture, key rules and adding providers.
unraid-management-agent copilot-instructions.md
Instructions for ruaan-deysel/unraid-management-agent, covering copilot instructions, copilot workflow, path-specific instructions, reusable prompts and quick commands.
coral CLAUDE.md
Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).