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 first-tree-ai/first-tree --skill first-tree-seedgit clone --depth 1 https://github.com/first-tree-ai/first-treeWrote 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/first-tree-ai/first-tree/first-tree-seed)<a href="https://agentmods.dev/skills/first-tree-ai/first-tree/first-tree-seed"><img src="https://agentmods.dev/badge/skills/first-tree-ai/first-tree/first-tree-seed/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/first-tree-ai/first-tree/first-tree-seed"><img src="https://agentmods.dev/badge/skills/first-tree-ai/first-tree/first-tree-seed.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 8 findings, 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 Prompt Injection · line 23 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Memory Poisoning · line 627 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Prompt Injection · line 627 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 627 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 631 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 1001 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 1006 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 1007 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00142 | $0.15423 |
| Opus 5.5 | $0.00057 | $0.06169 |
| Sonnet 5.5 | $0.00028 | $0.03085 |
| Haiku 4.5 | $0.00014 | $0.01542 |
Grade A, and why
first-tree-seed 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 — 1,229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
First Tree — Seed
Read this skill before drafting the first content into a Context Tree
that has no domain structure yet. It owns the bootstrap from "the tree has
no domain structure — either none exists, or a bound-but-empty one" to "the
tree has real top + second level structure plus initial leaf nodes drawn
from readable source repos". It first resolves the tree's state, then — for
a tree that needs building — creates the repo with first-tree tree init
when none exists (see Resolve the tree's state). Every subsequent write —
one PR/MR at a time, one decision at a time — belongs to first-tree-write,
not here.
When To Use This Skill
Use first-tree-seed |
Use a different skill |
|---|---|
| The team has no tree yet, or a bound tree with no normal domain structure per the generated policy's content classes | The tree already has a normal domain structure → first-tree-write (incremental source-driven write) |
| First content pass on resolved readable sources | Broad maintenance or drift-audit work on an existing tree |
| Invoked by name — by a human, an agent, or an onboarding kickoff prompt (see Resolve the tree's state) | Not an org admin, or the selected provider's local gh / glab identity is unauthenticated, and the team has no tree |
The skill is single-shot per tree setup: once the tree has domain
structure, a new or unrelated seed request refuses and routes further work
through first-tree-write or a focused maintenance task. The one exception is
a verified Phase 2 continuation recovered from the merged Tree's durable Seed
progress and exact source ledger. It may run in a new process, agent, or chat;
it is completion of the same seed, not a second seed.
What ships with it
3 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 First seen · 1,229 lines · 142 tokens per session scan A 880a8e9a0750
first-tree-seed is a skill published in the GitHub repository first-tree-ai/first-tree (157 stars, last pushed 8d ago), licensed Apache-2.0. It adds 142 tokens to every session and 15,423 once invoked, about $0.0006 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
first-tree-sync
Audit and repair drift between merged code and the Context Tree in both directions — tree→code (does code still support tree facts?) and code→tree (does the tree register everything code now contains?). Use when the tree may be stale, wrong, outdated, or missing coverage for recent code changes; after a large merge…
first-tree-write
Write Context Tree updates from explicit source material — code PRs, design docs, meeting notes, raw text. Use when the user gives you a concrete source and wants the right durable tree change drafted, linked, and reviewed. This skill is source-driven and targeted; use first-tree-sync instead for broad drift audits…
first-tree
Canonical whitepaper and routing skill for First Tree. Explains what belongs in a Context Tree, how source or workspace roots, tree repos, and bindings relate, and how the current first-tree tree and first-tree github scan surfaces fit together. Use when you need shared First Tree concepts, need to choose between…
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory for MiniMax Code. Recall durable context, store important facts and decisions, and link related memories with the mnemon CLI.