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 agentmods add skills/linkpranay-ai/context-engineering-protocol/ult-cep-wizardnpx skills add linkpranay-ai/context-engineering-protocol --skill ult-cep-wizardgit clone --depth 1 https://github.com/linkpranay-ai/context-engineering-protocolWrote 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/linkpranay-ai/context-engineering-protocol/ult-cep-wizard)<a href="https://agentmods.dev/skills/linkpranay-ai/context-engineering-protocol/ult-cep-wizard"><img src="https://agentmods.dev/badge/skills/linkpranay-ai/context-engineering-protocol/ult-cep-wizard.svg" alt="Measured on agentmods" 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 | $0.00168 | $0.03699 |
| Opus 5 | $0.00084 | $0.01850 |
| Sonnet 5 | $0.00034 | $0.00740 |
| Haiku 4.5 | $0.00017 | $0.00370 |
Grade A, and why
cep-wizard 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 2d 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ult-cep-wizard
Status: Phase 0 (read) + Phase 1 (write) + Phase 2 (guided brownfield onboarding)
complete (D24). Journey 3 (consumer/retrofit) also complete, see below. A thin,
user-launched, localhost-only local server that reads a
project's resolved ult-repo-layout state through four labeled boxes (What, How,
Guidelines, Trip-wire) and a server-rendered directory picker, and lets you resolve
each PENDING layout decision discover left behind — confirm the default, pick a
custom directory, skip, disable, or acknowledge — and Apply everything staged into
context-config.yaml in one step. The core rule is wizard-proposes, CLI-commits
(§18.3): the wizard only ever edits decision lines in
context-layout-discovery.md; the actual commit always goes through
ult-repo-layout's own confirm_layers.run_confirm(), called in-process, never
reimplemented. As of Phase 2, the server also always binds — even against a project
that hasn't discovered its layout yet, or whose layout config is currently broken —
and guides you through getting there instead of refusing to start; see "Guided setup"
below. See references/wizard-security-model.md,
references/wizard-picker-and-boxes.md,
references/wizard-write-path.md, and
references/wizard-onboarding-state-machine.md
for the full design; design decision D24 in
references/design-scratchpad-glossary.md.
The docs viewer described below (top bar + in-app PROTOCOL.md/README.md/case-study
rendering) is also part of D24; its routes' security model is in
references/wizard-security-model.md's §8.
Prerequisite
This skill only requires ult-repo-layout to be installed in the target repo
(SKILL.md + scripts/validate_layout.py present) — it no longer requires the repo to
already be initialized; that's now a guided in-browser step, not a precondition. It is
still a second-step tool relative to ult-repo-layout itself, not a replacement for
it — see ult-repo-layout's own SKILL.md.
scripts/wizard_preflight.py enforces the one remaining check: no socket opens and no
token is minted until ult-repo-layout is found installed.
What ships with it
59 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.
- references/wizard-onboarding-state-machine.md 9.4 KB
- references/wizard-picker-and-boxes.md 8.5 KB
- references/wizard-retrofit-flow.md 20 KB
- references/wizard-security-model.md 19 KB
- references/wizard-write-path.md 17 KB
- scripts/static/index.html 37 KB
- scripts/static/wizard.css 36 KB
- scripts/static/wizard.js 94 KB runs code
- scripts/tests/manual_playwright_box_files.py 18 KB runs code
- scripts/tests/manual_smoke_onboarding.md 9.8 KB
- scripts/tests/test_wizard_apply.py 11 KB runs code
- scripts/tests/test_wizard_atomic_write.py 2.4 KB runs code
- scripts/tests/test_wizard_auth.py 6.1 KB runs code
- scripts/tests/test_wizard_box_files.py 4.0 KB runs code
- scripts/tests/test_wizard_boxes.py 9.9 KB runs code
- scripts/tests/test_wizard_containment.py 16 KB runs code
- scripts/tests/test_wizard_content_hash.py 4.9 KB runs code
- scripts/tests/test_wizard_decision_staging.py 15 KB runs code
- scripts/tests/test_wizard_discover.py 6.9 KB runs code
- scripts/tests/test_wizard_docs.py 15 KB runs code
- scripts/tests/test_wizard_init.py 10.0 KB runs code
- scripts/tests/test_wizard_layout_source.py 12 KB runs code
- scripts/tests/test_wizard_markdown.py 13 KB runs code
- scripts/tests/test_wizard_onboarding_state.py 12 KB runs code
- scripts/tests/test_wizard_originhost.py 5.9 KB runs code
- scripts/tests/test_wizard_picker.py 4.4 KB runs code
- scripts/tests/test_wizard_preflight.py 5.0 KB runs code
- scripts/tests/test_wizard_retrofit_apply.py 20 KB runs code
- scripts/tests/test_wizard_retrofit_draft.py 26 KB runs code
- scripts/tests/test_wizard_retrofit_inventory.py 30 KB runs code
- scripts/tests/test_wizard_retrofit_state.py 14 KB runs code
- scripts/tests/test_wizard_server.py 96 KB runs code
- scripts/tests/test_wizard_stub_content.py 11 KB runs code
- scripts/tests/test_wizard_tripwire.py 7.7 KB runs code
- scripts/wizard_apply.py 7.2 KB runs code
- scripts/wizard_atomic_write.py 3.1 KB runs code
- scripts/wizard_auth.py 6.1 KB runs code
- scripts/wizard_box_files.py 4.2 KB runs code
- scripts/wizard_boxes.py 5.7 KB runs code
- scripts/wizard_containment.py 15 KB runs code
- scripts/wizard_content_hash.py 2.9 KB runs code
- scripts/wizard_decision_staging.py 13 KB runs code
- scripts/wizard_discover.py 6.2 KB runs code
- scripts/wizard_docs.py 13 KB runs code
- scripts/wizard_e2e_check.py 10 KB runs code
- scripts/wizard_init.py 8.3 KB runs code
- scripts/wizard_layout_source.py 15 KB runs code
- scripts/wizard_markdown.py 22 KB runs code
- scripts/wizard_onboarding_state.py 8.4 KB runs code
- scripts/wizard_originhost.py 3.3 KB runs code
- scripts/wizard_picker.py 4.1 KB runs code
- scripts/wizard_preflight.py 4.1 KB runs code
- scripts/wizard_retrofit_apply.py 12 KB runs code
- scripts/wizard_retrofit_draft.py 25 KB runs code
- scripts/wizard_retrofit_inventory.py 20 KB runs code
- scripts/wizard_retrofit_state.py 8.8 KB runs code
- scripts/wizard_server.py 64 KB runs code
- scripts/wizard_stub_content.py 13 KB runs code
- scripts/wizard_tripwire.py 5.2 KB runs code
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.
- 2d ago Changed · +8 lines 01386abe6cfa
- 6d ago First seen · 225 lines · 168 tokens per session scan A 6de3975f8164
cep-wizard is a skill published in the GitHub repository linkpranay-ai/context-engineering-protocol (8 stars, last pushed 3d ago), licensed Apache-2.0. It adds 168 tokens to every session and 3,699 once invoked, about $0.0008 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
carryover
Use when recalling, saving or curating carryover memory, wikis, playbooks or the Obsidian vault.
bootstrap-llm-synthesis
Construct the LLM synthesis prompt from project surface scan + optional tree-sitter context + optional Q&A answers. Call the LLM. Parse and validate the response into 6-8 structured memory entries with clarity tags and source traceability. Used as Stage 3 of the /gaai:bootstrap pipeline.
memory-reconcile
Scan all memory files, documentation (/docs//.md), and README files (/README.md) for drift, contradictions, and stale references. Produce a reconciliation report for Discovery to action. Activate on demand or via cron.
memory-archive-superseded
Migrate a superseded DEC's index rows from active index.md to archive/superseded-decisions.archive.md. Idempotent. Discovery-only — never invoked by daemon delivery. Updates DEC frontmatter as canonical source of truth.
memory-delta-triage
Apply three deterministic heuristics to a single memory-delta file to produce a structured verdict block; invoke memory-ingest on ACCEPTED candidates only in validate mode. Activate when Discovery processes a raw memory-delta from contexts/artefacts/memory-deltas/.
decision-extraction
Identify and formalize durable product and technical decisions from agent outputs into long-term memory. Activate after Discovery produces artefacts, Delivery resolves trade-offs, or product direction materially changes.