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 skills add nasrulhazim/claude --skill project-conventionsgit clone --depth 1 https://github.com/nasrulhazim/claudeWrote 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/nasrulhazim/claude/project-conventions)<a href="https://agentmods.dev/skills/nasrulhazim/claude/project-conventions"><img src="https://agentmods.dev/badge/skills/nasrulhazim/claude/project-conventions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nasrulhazim/claude/project-conventions"><img src="https://agentmods.dev/badge/skills/nasrulhazim/claude/project-conventions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 5 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 18 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Excessive Agency · line 135 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 5.1 | $0.00172 | $0.02445 |
| Opus 5 | $0.00086 | $0.01222 |
| Sonnet 5 | $0.00034 | $0.00489 |
| Haiku 4.5 | $0.00017 | $0.00245 |
Grade A, and why
project-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 10d 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Update Practice
CLAUDE.md is a living document. Claude must update it immediately whenever something
worth remembering is discovered — corrections, preferences, patterns, or gotchas.
The rule: A slightly redundant note is better than repeating a mistake.
When to Update CLAUDE.md
Update immediately when any of these occur:
| Trigger | Example |
|---|---|
| User corrects a mistake | "jangan guna MySQL, kita pakai PostgreSQL" |
| User expresses a preference | "aku tak suka pattern ni, guna cara lain" |
| Better pattern discovered during implementation | Realising a cleaner approach mid-task |
| Gotcha or edge case found | A library behaves unexpectedly, an assumption was wrong |
| Architectural decision made | "kita guna UUIDs, bukan auto-increment" |
| Naming or style preference | "method names in camelCase, not snake_case" |
| Tool or stack choice confirmed | "pakai Pest, bukan PHPUnit" |
| Testing preference confirmed | "pakai Pest describe blocks", "PHPStan level 8" |
| Deployment preference confirmed | "deploy via GitHub Actions", "Docker for staging" |
Do not wait until the end of the session. Update CLAUDE.md as soon as the
correction or preference is identified — then continue with the task.
Update Procedure
When a trigger is detected:
- Apply the fix to the current task first
- Read the current
CLAUDE.mdto find the right section - Insert the update in the appropriate section:
- Preference / style →
## Preferencesor relevant stack section - DO/DON'T →
## DO / DON'T - Architectural → update the relevant architecture section
- Gotcha / edge case → add under the relevant section with
> **Gotcha:**callout
- Preference / style →
- Do not announce every update unless the user asks — just do it silently and continue
Format Rules
Gotcha Format
> **Gotcha:** PostgreSQL `uuid-ossp` extension must be enabled before using
> `DB::raw('uuid_generate_v4()')`. Prefer letting Laravel handle UUID generation
> from PHP side via `InteractsWithUuid` trait instead.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 272 lines · 172 tokens per session scan A 1d0b71827681
project-conventions is a skill published in the GitHub repository nasrulhazim/claude (22 stars, last pushed 7d ago), licensed MIT. It adds 172 tokens to every session and 2,445 once invoked, about $0.0009 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…