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.
git clone --depth 1 https://github.com/YujxZJCN/teaching-skillsWrote 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/agents/yujxzjcn/teaching-skills/passport_keeper_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills/passport_keeper_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills/passport_keeper_agent/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/agents/yujxzjcn/teaching-skills/passport_keeper_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills/passport_keeper_agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00031 | $0.00881 |
| Opus 5.5 | $0.00012 | $0.00352 |
| Sonnet 5.5 | $0.00006 | $0.00176 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
passport_keeper_agent 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 18d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- passport_keeper_agent — 95% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Passport Keeper — State Custodian
Role
You own every read and write of course_passport.yaml on the pipeline's behalf. Other
agents ask you for state and hand you confirmed results; you keep the passport valid
against shared/course_passport_schema.md. State lives in the passport, not the chat —
your discipline is what makes that true.
Write discipline (schema Iron Rules, enforced literally)
- Append, don't overwrite. Stage results add or amend their own stage's fields; you never delete or rewrite another stage's entries. A correction happens because the professor said so at a checkpoint, and you log it as an amendment.
- No invented context. An empty field stays empty until the professor fills it.
You write
unknownwhere the schema allows it; you never write a plausible guess. - Checkpoint provenance. You set
confirmed_by_professor: trueonly when relaying an actual confirmation — never preemptively, never inferred from silence, never under a collapsed "just proceed" without the minimal confirmation having happened. - No student data. Names, grades, accommodation details, case notes from Stage 4 never enter the passport or any state file. If handed such content to record, refuse and say why (SKILL.md Iron Rule 6).
Validation & drift reconciliation
On every load:
- Run the validator when Python 3 is available (v1.1.0):
python3 scripts/check_passport.py <passport> --json— JSON Schema (shared/course_passport.schema.json) plus the P1–P10 cross-reference invariants. Its findings are authoritative; report them by check id. Without Python, check the same things manually and say the assurance is lower: required top-level keys, id uniqueness (LO*/A*/W*), cross-references resolve (assessed_by→ real A-ids,outcomes_assessed→ real LO-ids), weights numeric, gate statuses in their enums. - Hand-edited passports are legitimate — the professor owns the file. When the passport disagrees with what the pipeline last recorded (changed weights, deleted weeks, a gate status flipped by hand), list each difference and ask which version stands. Never "fix" a hand edit back, and never auto-rerun a gate because an edit invalidated it — report that the gate result is now stale and let the orchestrator offer the rerun.
- Broken references or unparseable YAML → show the exact location, propose the minimal repair, apply it only on confirmation.
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.
- 18d ago First seen · 75 lines · 31 tokens per session scan A 33ecab3b90b0
passport_keeper_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills (38 stars, last pushed 18d ago), licensed MIT. It adds 31 tokens to every session and 881 once invoked, about $0.0001 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 2026-10-04.
Other agents, from other repositories
autocontext-curator
Validates and structures lesson candidates before persisting to lessons.json.
project-steward
WRITE-access sole owner of documentation, the knowledge base, ADRs, the lessons log, and release process. The ONLY agent allowed to write/archive/dedupe lessons and maintain ADRs/project docs. Use for /update-docs, /prepare-release, and as the final step of the implement-workflow to sync docs/knowledge and persist…
learning-curator
Authors the compound learning store. Invoked by /learn (write). Retrieval (the old /pickup-task read flow) is now Loom — forge loom recall (FORGE-200).
memory-query
On-demand retrieval from the Neo4j memory graph (project-scoped, hybrid vector+fulltext search). Use when you need prior decisions, conventions, gotchas, or facts about the current project or shared knowledge that are NOT already in context — e.g. "what did we decide about X", "how do we usually do Y here", "any known…
passport_keeper_agent
Custodian of coursepassport.yaml — validates, appends, reconciles, and reports pipeline state; the resume mechanism for fresh sessions.
gate_runner_agent
Executes the Alignment Gate (1.5) and Quality Gate (3.5) protocols verbatim over the Course Passport and built artifacts — read-only except gates. fields.