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 skills/sandydasari/openacme/coding-conventionsnpx skills add sandydasari/openacme --skill coding-conventionsgit clone --depth 1 https://github.com/sandydasari/openacmeWrote 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/skills/sandydasari/openacme/coding-conventions)<a href="https://agentmods.dev/skills/sandydasari/openacme/coding-conventions"><img src="https://agentmods.dev/badge/skills/sandydasari/openacme/coding-conventions.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 | $0.00027 | $0.00602 |
| Opus 5 | $0.00014 | $0.00301 |
| Sonnet 5 | $0.00005 | $0.00120 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
coding-conventions 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding conventions
Generic guardrails for any agent that writes or modifies code. Load this skill when you're about to touch a codebase you don't fully own.
Read before you write
Read the file you're about to modify. Read its callers. Read the test that covers it. The shape that already exists is the shape — match it. Don't introduce a new file layout, a new abstraction, or a new dependency just because it feels cleaner to you in isolation.
Smallest viable change
The diff should answer the request and nothing else. If the request says "fix bug X," your diff fixes bug X — it does not also reformat the file, rename three identifiers, extract a helper, or upgrade a dependency. Each of those is a separate decision the user has not made yet.
Three similar lines beats a premature abstraction. Wait for the fourth before factoring.
Comments
Default: don't write one. Names and types do the explaining. Add a comment only when the why is genuinely non-obvious — a hidden invariant, a subtle ordering constraint, a workaround for a specific upstream bug. Keep it one line. Don't explain what the code does; the reader can see that.
Never write multi-paragraph docstrings. Never reference the current ticket or the caller list — both rot.
Types
Prefer narrow types over any / unknown / wide unions. Make illegal states unrepresentable when it's cheap.
When validating data crossing a boundary (HTTP, files, env vars), validate once at the boundary and trust the type inside. Don't re-validate in every internal function.
Errors
Throw Error with a clear, specific message. Don't swallow. Don't wrap in try/catch just to log-and-rethrow.
Don't add error handling for cases that can't happen. Trust internal invariants; only validate at boundaries.
Dependencies
Don't add a dependency for something you can write in 20 lines. Don't add a dependency that pulls in 200 transitive packages for one helper.
When you do add one, prefer the standard already in use in this repo over a "better" alternative. Consistency beats individual optimization.
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 · 54 lines · 27 tokens per session scan A 9902b71993d6
coding-conventions is a skill published in the GitHub repository sandydasari/openacme (86 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 602 once invoked, about $0.0001 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 skills, from other repositories
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.worker-delegation
Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
hive.writing-hive-skills
Author a new Agent Skill for a Hive agent that conforms to the Agent Skills specification (SKILL.md with YAML frontmatter, optional scripts/references/assets directories). Use when the user asks to create, scaffold, add, or package a new skill for a Hive agent.