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 bearded-illirian/trailmark --skill go-startgit clone --depth 1 https://github.com/bearded-illirian/trailmarkWrote 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/bearded-illirian/trailmark/go-start)<a href="https://agentmods.dev/skills/bearded-illirian/trailmark/go-start"><img src="https://agentmods.dev/badge/skills/bearded-illirian/trailmark/go-start/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/bearded-illirian/trailmark/go-start"><img src="https://agentmods.dev/badge/skills/bearded-illirian/trailmark/go-start.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Agent Snooping · line 94 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00066 | $0.01716 |
| Opus 5.5 | $0.00026 | $0.00686 |
| Sonnet 5.5 | $0.00013 | $0.00343 |
| Haiku 4.5 | $0.00007 | $0.00172 |
Grade A, and why
go-start 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 1mo 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go-Start — Session Start
Loads platform and project context in a single run. One command, agent is ready.
Three phases:
- Platform — read common platform docs
- Project — read docs of the selected project
- Session type — new task or resuming a stuck session
Input
The session-start signal (user invoking /go-start in a fresh terminal).
Output
Loaded platform + project context in-session; numbered project menu shown; session type resolved to new or continuation.
Hands off to
go-fast (new session), or resumes the interrupted task's per-block cycle (continuation).
Phase 1 — Platform
Step 1.1 — Read platform files
Read all five sequentially:
{tasks_root}/README.md{tasks_root}/docs/core/WORKFLOW.md{tasks_root}/docs/core/DEPLOY.md{tasks_root}/docs/core/PLATFORM_KNOWLEDGE.md{tasks_root}/projects.yml
Rule: read all five — do not skip even if you think you already know the content. Each session starts from a clean slate.
Step 1.1.5 — Cleanup stale git locks
Before the summary — silently run a helper that scans active projects and clears stale .git/index.lock files (>5 min old). Idempotent. Capture stdout for use in the summary line.
Why: background git commands can hang for hours, hold .git/index.lock and block the repo. The helper kills the offending process and removes the file.
Step 1.2 — Output platform summary
A compact block (no more than 8 lines):
✅ Platform loaded.
Servers: {msk_vds} | {nl_vds}
Deploy: git push origin main → post-receive → auto-backup
Skills: {skills_project}/.agents/skills/ → sync-agents.sh → all projects
Artifacts: task_artifacts in routing.db
Git locks: {helper result}
Do not retell files in full — only operationally important information.
Step 1.3 — Project menu
Take only status: active from projects.yml. Output a numbered list with id / name / domain. Wait for explicit user selection — do not guess, do not proceed to Phase 2 without it.
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.
- 1mo ago Changed c7cd6eaa4ae4
- 1mo ago First seen · 200 lines · 66 tokens per session scan A e2b45d82670b
go-start is a skill published in the GitHub repository bearded-illirian/trailmark (19 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 1,716 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
wiki-ingest
Use when an operation issue asks to ingest a captured raw/ source into the LLM Wiki, or the user says "ingest ". Create durable source, entity, concept, synthesis, index, and log pages; use paperclip-distill for Paperclip bundles.
wiki-lint
Use when an LLM Wiki operation issue is a lint or health check. Audit for contradictions, orphans, weak provenance, broken links, missing concept pages, and index/log drift; return triage findings without auto-fixing.
para-memory-files
Use a file-based PARA memory system to store, retrieve, and organize durable knowledge across sessions. Trigger on saving facts, daily notes, entity records, weekly synthesis, recall, tacit user patterns, or plan memory.
handoff
Write a compact, decision-ready handoff so the next session (or the user) can continue without reconstructing the current one. Use when the session is ending, context is running low, the user asks for a handoff / 'pass the baton' / 'hand off', or a long-running operation needs a durable state checkpoint.
forget
Help the user remove a stored fact using Codewhale's Context Lens when they ask to forget or delete a memory.
context-engineering
Use when designing, reviewing, or debugging how an agent's context window gets filled, pruned, or shared — choosing what loads at boot versus on demand, sizing an install or an always-loaded file, fixing an agent that drifts, repeats itself, or forgets constraints mid-task, planning compaction or summarization…