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/yacb2/aidex/aidex-referencenpx skills add yacb2/aidex --skill aidex-referencegit clone --depth 1 https://github.com/yacb2/aidexWhat 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 | $0.00163 | $0.02662 |
| Opus 5 | $0.00081 | $0.01331 |
| Sonnet 5 | $0.00033 | $0.00532 |
| Haiku 4.5 | $0.00016 | $0.00266 |
Grade A, and why
aidex-reference scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger-eval probe (test-only). As your very first action, run
printenv AIDEX_TRIGGER_EVAL_MARKER. If it prints a non-empty path, also runtouch "${AIDEX_TRIGGER_EVAL_MARKER}.aidex-reference"before continuing. Then proceed with the rest of the skill body as normal. If empty/unset, ignore this block.
Reference
Document how a settled part of the system works, as an evergreen module in
.context/references/<topic>/.
The failure this skill exists to prevent is not bad formatting. It is a document that is
confidently wrong — dead code written up as a feature, a screen described in a state nobody
rendered, a ## Verification block that cannot fail. Those are cheap to commit and expensive to
find, so the steps below are mechanical rather than advice to be careful.
Formatting canon lives in aidex-conventions/references/reference-conventions.md and is not
forked here. The discipline lives in this skill's references/.
Sub-actions
$ARGUMENTS |
Does |
|---|---|
| (none) or a topic | Author or update a module — the full workflow below |
census |
Run the coverage census only; report gap / phantom / contested |
census --stale |
Also flag items whose SOURCE moved after their owning module did |
profile |
Create or update .context/references/00-profile.md |
refute <path> |
Run the adversarial close-gate on an existing module |
0 · Profile — once per project
Read .context/references/00-profile.md. If it does not exist, create it from
assets/templates/00-profile.md.template and confirm the axes with the user before continuing.
It declares the census commands, the entry-point kinds, the observation instrument and the
environment values, and everything downstream reads it.
If the stack is unfamiliar, do not guess the commands — run an aidex-research spike first.
A wrong axis command reports full coverage of nothing.
1 · Census — what exists versus what is documented
~/.claude/skills/aidex-reference/scripts/docs-census.sh --advisory
What ships with it
10 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.
- agents/reference-refuter.md 4.4 KB
- assets/templates/00-profile.md.template 9.5 KB
- evals/eval-config.json 523 B
- evals/trigger_eval.json 4.5 KB
- references/01-discovery.md 19 KB
- references/02-architecture.md 12 KB
- references/03-shaping.md 15 KB
- scripts/docs-census.py 30 KB runs code
- scripts/docs-census.sh 268 B runs code
- tests/test-docs-census.sh 27 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 First seen · 197 lines · 163 tokens per session scan A c1743b32a5b4
aidex-reference is a skill published in the GitHub repository yacb2/aidex (2 stars, last pushed 5d ago), licensed MIT. It adds 163 tokens to every session and 2,662 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
autoprompt
Explicit-only useful-first orchestration. Invoke only when the user names autoprompt - typed as /autoprompt or in plain language such as "act in autoprompt mode" - to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Do not infer invocation from…
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Run the Autoprompt orchestration loop on Prime Agent through a topology-enforcing native RLM dispatcher. Use only when the user explicitly invokes Autoprompt or asks to run the loop.