Borrowing it
Nothing to install: this file belongs to zkysar1/Claude-Mind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zkysar1/Claude-Mind/main/.claude/skills/curriculum-gates/SKILL.mdgit clone --depth 1 https://github.com/zkysar1/Claude-MindWrote 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/zkysar1/claude-mind/curriculum-gates)<a href="https://agentmods.dev/skills/zkysar1/claude-mind/curriculum-gates"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/curriculum-gates/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/zkysar1/claude-mind/curriculum-gates"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/curriculum-gates.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00101 | $0.03426 |
| Opus 5 | $0.00051 | $0.01713 |
| Sonnet 5 | $0.00020 | $0.00685 |
| Haiku 4.5 | $0.00010 | $0.00343 |
Grade A, and why
curriculum-gates 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/curriculum-gates — Curriculum Gate Evaluation & Promotion
Evaluates all graduation gates for the agent's current curriculum stage.
If all gates pass, promotes the agent to the next stage and logs the promotion.
Called by /aspirations-consolidate (session end) and /aspirations-evolve (evolution cycle).
Step 0: Load Conventions — Bash: load-conventions.sh with each name from the conventions: front matter. Read only the paths returned (files not yet in context). If output is empty, all conventions already loaded — proceed to next step.
Step 1: Evaluate Gates
Bash: curriculum-evaluate.sh → parse JSON output
IF configured == false:
Bash: echo "Curriculum: Not configured — skipping gate evaluation."
RETURN
IF terminal_stage == true:
Bash: echo "Curriculum: At terminal stage — all capabilities unlocked."
RETURN
Output: "Curriculum gate evaluation for stage: {stage_name}"
For each gate in gates:
Output: " {gate.id}: {PASS/FAIL} (current: {current_value}, required: {operator} {threshold})"
Output: "Gates passed: {gates_passed_count}/{gates_total}"
Step 2: Promote If Ready — guard-33 Autonomous Self-Escalation Chokepoint
A curriculum promotion is a capability-unlock self-escalation: it unlocks
gated capabilities (self-edits, forge-skill, parallelism) and can REVERSE a
prior resolved self.md decision (e.g. "no bidding before Stage 1"). guard-33
forbids the agent self-authorizing such an action. The assistant-mode path
(/respond Step 5.0) already routes user-directed escalations through the
email round-trip; this is the autonomous-origin counterpart so guard-33
holds regardless of origin. Protocol:
world/conventions/self-escalation-confirmation.md.
Autonomous mode MUST NOT block on user input (no-blocking-in-RUNNING-state),
so the pattern is register + DEFER, never register-and-wait. The promotion
is gated behind a confirmed pending-escalation record and applied on a LATER
curriculum-gates run, once the user's YES has been parsed by the domain
inbox-poll skill (see world/conventions/self-escalation-confirmation.md). The
escalation store IS the state machine
(awaiting_reply -> confirmed | denied | timed_out) --- there is no marker file;
agents/<agent>/session/pending-escalations.yaml is the single source of truth.
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 · 244 lines · 101 tokens per session scan A d31d99b71305
curriculum-gates is a skill published in the GitHub repository zkysar1/Claude-Mind (5 stars, last pushed 2d ago), licensed MIT. It adds 101 tokens to every session and 3,426 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
interview-prep
Technical interview preparation expert for algorithms, system design, and behavioral questions.
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.worker-delegation
Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
hive.pdf
Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…