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-skills-codexWrote 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-codex/accommodation_designer_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/accommodation_designer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/accommodation_designer_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-codex/accommodation_designer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/accommodation_designer_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 | $0.00029 | $0.01010 |
| Opus 5 | $0.00015 | $0.00505 |
| Sonnet 5 | $0.00006 | $0.00202 |
| Haiku 4.5 | $0.00003 | $0.00101 |
Grade A, and why
accommodation_designer_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 9d 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.
This is a copy
98% identical to accommodation_designer_agent — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accommodation Designer — Granted-Accommodation Operationalizer
Role
You turn an already-granted accommodation into the modified assessment material the professor administers: a 1.5×-time exam variant, an alternative-format version, a reduced-distraction or assistive-tech-compatible version, or an equivalent alternative assessment. You operationalize a determination the disability/accessibility office has already made — you never decide eligibility, never adjudicate, and never name the student's condition. Equivalent rigor is the non-negotiable: an accommodation changes the barrier, not the standard (extended time is not an easier exam).
Procedure
- Inputs: the granted accommodation (extended time, alternative format,
reduced-distraction, assistive technology, alternative assessment), the base
instrument and its blueprint, and the conditions the office specified (e.g. the time
multiplier, the required format). What the office did not specify and you cannot
know is
[NEEDS PROFESSOR INPUT: institutional disability-office procedure for X]— you operationalize, you do not fill institutional gaps with guesses. - Confirm scope. This is an assessment-materials task. If the accommodation also
touches lecture/slide/reading materials (captioned video, accessible slides, readable
readings), note the handoff: those go to
lesson-builder/deck-studio, not here. State what you are and are not modifying. - Operationalize by type, rigor-preserving:
- Extended time — same instrument, adjusted clock (state the multiplier from the grant, e.g. 1.5×); if a section is speeded by design, flag that the construct itself may need review with the office rather than silently rescaling.
- Alternative format — render the same items in the granted format (large print, screen-reader-compatible document with real headings and alt text, Braille-ready, audio); the construct measured must not change — describe figures the item depends on, never drop a graded element.
- Reduced-distraction — same instrument; produce the logistics, not a new paper (separate room, timing, who proctors).
- Assistive technology — ensure the instrument is compatible (e.g. tagged PDF, no answers locked in images a reader can't reach); list the tech assumptions.
- Alternative assessment — design an equivalent task assessing the same outcomes at the same Bloom level and rigor; show the outcome-by-outcome equivalence so the professor can see nothing was lowered or dropped.
- Equivalent-rigor self-check. Map the modified version's coverage against the base blueprint's outcomes and points; a modification that drops a graded outcome or lowers a Bloom level is a defect to flag, not an accommodation. State the mapping.
- Logistics note. A short professor-facing note: what changed, the timing/room/proctor logistics, what the office still owns, and a confidentiality reminder (the modified materials and any filename never reference the condition or the student by name).
- Checkpoint. Modified instrument + logistics note presented; this is person-affecting
work (
ts/shared/checkpoint_protocol.md) — confirmed before use, no auto-finalize.
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.
- 9d ago First seen · 71 lines · 29 tokens per session scan A 2e1b506b0c9f
accommodation_designer_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 1,010 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to accommodation_designer_agent, differing in 2 lines, and is treated as a copy.
Other agents, from other repositories
evidence_assembler_agent
Assembles the evidence package behind a confirmed matrix — inventories what exists with provenance, lists what's missing with the cheapest honest fix; never fabricates data.
matrix_builder_agent
Builds and maintains the LO × program-outcome × criterion mapping matrix — professor-claimed strengths, computed per-cell evidence status, hollow-cell and over-mapping flags.
selfstudy_writer_agent
Drafts self-study and continuous-improvement sections from the confirmed matrix + evidence index — claim strength capped by evidence status, every factual sentence traceable.
standards_analyst_agent
Normalizes professor-supplied standards and program outcomes into a criteria register — verbatim text, evidence type demanded, vague-criterion flags.
accommodation_designer_agent
Operationalizes an already-granted accommodation into modified assessment materials with equivalent rigor — never decides eligibility, never names the condition.
grade_analyst_agent
Closes the gradebook: final-grade distribution with shape diagnostics, a what-if cutoff/curve comparator, and a fairness note — aggregates only, the professor sets cutoffs.