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 sammcj/agentic-coding --skill skill-creator-primergit clone --depth 1 https://github.com/sammcj/agentic-codingWrote 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/sammcj/agentic-coding/skill-creator-primer)<a href="https://agentmods.dev/skills/sammcj/agentic-coding/skill-creator-primer"><img src="https://agentmods.dev/badge/skills/sammcj/agentic-coding/skill-creator-primer/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/sammcj/agentic-coding/skill-creator-primer"><img src="https://agentmods.dev/badge/skills/sammcj/agentic-coding/skill-creator-primer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 280 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 392 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.
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 | $0.00074 | $0.08696 |
| Opus 5.5 | $0.00030 | $0.03478 |
| Sonnet 5.5 | $0.00015 | $0.01739 |
| Haiku 4.5 | $0.00007 | $0.00870 |
Grade A, and why
skill-creator-primer 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 — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator Primer
Note: If the skill-creator skill is missing: stop and ask the user to install skill-creator@claude-plugins-official (registering the marketplace first via /plugin marketplace add anthropics/claude-plugins-official if needed), or to clone https://github.com/anthropics/skills and link its skills directory into their local skills directory.
Route to an entry point by the task in front of you (which-one routing per "Routing when branches multiply", not a content index):
- Creating a new skill -> start at "Capture Intent from Conversation" and work forward.
- Editing an existing skill -> the sections covering what you're changing, then the "Self-Review Protocol".
- Reviewing a skill, or a diff to one -> "Reviewing a Skill".
- Tuning a description or its triggering -> "Writing Effective Descriptions".
- Producing a report, page or visual of a skill's findings ->
references/html-report.md.
Predictable Process, Not Identical Output
A skill wrangles determinism out of a stochastic system where applicable. What it makes predictable is the process - the agent taking the same steps each run - not the output. A brainstorming skill should predictably diverge: its tokens vary, its behaviour doesn't. This is the lens for the rest of this primer: triggering, structure, steering, and pruning are all levers on process consistency; cost and maintainability follow. Judge any change by whether it makes the agent behave more consistently, given what that particular skill is for.
Track Each Step as a Task
Before you create, update, or review a skill, create a task (todo) for each step of the work - the primer sections you'll apply, plus a self-review pass - each phrased with its completion criterion, then work them to completion.
- This is the primer's own defence against premature completion: with the finish line in view, the agent tends to make the visible edit and skip the review. Tracked tasks keep the whole process in front of you.
- Scale the ceremony to the change: substantial skill work warrants a task per step; a trivial edit still earns its description update, a trigger-conflict check, and a self-review pass, tracked or not.
What ships with it
17 files 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.
- assets/skill-template.md 963 B
- CHANGELOG.md 32 KB
- CLAUDE.md 3.2 KB
- evals/trigger.json 3.0 KB
- references/html-report.md 2.7 KB
- references/steering.md 2.7 KB
- references/trigger-evals.md 2.4 KB
- ruff.toml 982 B
- scripts/eval_triggering.py 8.2 KB runs code
- scripts/hook_report_skill_tokens.py 2.3 KB runs code
- scripts/list_descriptions.py 1.9 KB runs code
- scripts/render_report.py 32 KB runs code
- scripts/report_assets.py 23 KB runs code
- scripts/report_model.py 28 KB runs code
- scripts/validate_skill.py 65 KB runs code
- tests/test_render_report.py 65 KB runs code
- tests/test_validate_skill.py 56 KB runs code
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 Changed · +7 lines b3890b69c938
- 8d ago Changed 5f6271bf82b8
- 1mo ago Changed 98783d55efae
- 1mo ago Changed · +2 lines fd8bbaf79c81
- 1mo ago Changed 78a4543fc095
- 1mo ago Changed · +6 lines a6deeb6b83ec
- 1mo ago First seen · 387 lines · 74 tokens per session scan A b176baae0c35
skill-creator-primer is a skill published in the GitHub repository sammcj/agentic-coding (165 stars, last pushed today), licensed Apache-2.0. It adds 74 tokens to every session and 8,696 once invoked, about $0.0003 per session on Opus 5.5. 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
agentproto-llm-endpoint
Use the local LLM endpoint proxy (localhost:18090) — or your own gated public deployment — to route Claude Code / Claude SDK through custom providers (OpenRouter, Moonshot, Groq, ZAI) via an Anthropic-compatible gateway. Covers adapter-specific behaviors, auth patterns, proxy codenames, and common failure modes.
agentpush
Bridge an imported agentpush MCP server (Telegram, WhatsApp, etc.) with live agentproto sessions via the daemon's transmitter subsystem: transmitmessage sends outbound and binds the recipient to a session, inboundwatcherstart polls agentpush for new messages, and inboundendpointcreate/POST /inbound(/:slug) route…
bureau
Drive Bureau — the browser stack's installable capability server: a stealth Firefox (Camofox) + daemon that exposes browser tools as MCP-over-HTTP on :8830, plus a CLI for saved browser identities (sessions), social capture / search, adapter health probes, declarative workflows, and Guilde connection. Use when working…
ap-workflows
Run multi-stage session pipelines with agentproto workflows — workflowstart with barrier-gated stages of concurrent steps, sessionRef to reuse earlier output, workflowstatus/cancel/retry, workflowrunfile for AIP-15 WORKFLOW.md, and workflowescalationresolve for human answers. Trigger when asked to pipeline agents, fan…
agentproto-apps
Author, develop, and package an agentproto APP (AIP-53) — the real CLI path: agentproto app init → edit .agentproto/ (APP.md, agents/, workflows/, ui/) → agentproto app validate → agentproto app dev / build / serve → agentproto app install → agentproto app pack. Covers the canonical file layout, APP.md frontmatter…
Drive the user's authenticated Instagram via the browser skill: profiles, media likers/comments, followers/following, search via the web private API; gated like/comment/follow/DM. Use for Instagram research/outreach as the user.