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 ship-firstgit 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/ship-first)<a href="https://agentmods.dev/skills/bearded-illirian/trailmark/ship-first"><img src="https://agentmods.dev/badge/skills/bearded-illirian/trailmark/ship-first/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/ship-first"><img src="https://agentmods.dev/badge/skills/bearded-illirian/trailmark/ship-first.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 Excessive Agency · line 150 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 | $0.00068 | $0.02532 |
| Opus 5.5 | $0.00027 | $0.01013 |
| Sonnet 5.5 | $0.00014 | $0.00506 |
| Haiku 4.5 | $0.00007 | $0.00253 |
Grade A, and why
ship-first scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `backend` | curl / command from plan, check status + response | How it starts
The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship-First Protocol
Final protocol after task execution. Receives context from the calling skill:
{task_id}— slug or task id{artifact_type}—fast-trackortask{log_dir}— path to the log folder{task_file}— path to the original task file{project},{project_path}— from projects config{title}— task name (one line){date}— current date{arch_ref}— arch-map result (string or null){block_num}— current block number (per-block mode only)
Input
Complete block or task execution context — the report artifacts from plan-first, block-num or "final" marker, task_id, log_dir, project metadata.
Output
report-*.md + user-note-*.md per block; task-level aggregate user-note.md; STATUS.md in project root; routing.db row updated (status / arch_ref / closed_at); block or task marked done.
Hands off to
flow-first for the next open block (per-block mode), or — (terminal) when all blocks are done.
ship-first Modes
ship-first operates in two modes:
Per-block mode
Trigger: {block_num} is in context. Called by: plan-first after block execute. Does: writes report-N.M.md + user-note-N.M.md, deploys the block, runs smoke test, closes the block in task_blocks, then moves to the next block or switches to task-level mode.
Task-level mode
Trigger: {block_num} not passed or equals 'final'. Called by: decomposition orchestrators after all blocks are closed, or per-block ship-first when it sees no open blocks. Does: artifact completeness check, ui-ai-first if needed, aggregate final user-note, "close?" question, guide?, arch-map, routing.db update, propagate arch_ref, parent chain check, STATUS + sessions.
Mode determination
If {block_num} in context → per-block. Otherwise → task-level. Modes are mutually exclusive.
Per-block mode
Step B1 — Write report-N.M.md
Determine round {R}. Create {log_dir}/report-{N.M}.{R}.md with sections: What was done / What was notable / Next. Register in task_artifacts with artifact_type='report'.
What ships with it
2 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.
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 · +18 lines 92b3399f9511
- 1mo ago First seen · 232 lines · 68 tokens per session scan A 4d35d357dcdc
ship-first is a skill published in the GitHub repository bearded-illirian/trailmark (19 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 2,532 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
stub_distance_skill
a deterministic stub returned by the override engine in unit tests.
generated_skill_1775724185480
Parse XBRL financial documents and extract key taxonomy elements into structured JSON format.
paperclip
Use for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.