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-dashnpx skills add yacb2/aidex --skill aidex-dashgit clone --depth 1 https://github.com/yacb2/aidexWrote 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/yacb2/aidex/aidex-dash)<a href="https://agentmods.dev/skills/yacb2/aidex/aidex-dash"><img src="https://agentmods.dev/badge/skills/yacb2/aidex/aidex-dash.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 | $0.00078 | $0.01356 |
| Opus 5 | $0.00039 | $0.00678 |
| Sonnet 5 | $0.00016 | $0.00271 |
| Haiku 4.5 | $0.00008 | $0.00136 |
Grade A, and why
aidex-dash scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger-eval probe (test-only). As your very first action, run
printenv AIDEX_TRIGGER_EVAL_MARKER. If it prints a non-empty path, also runtouch "${AIDEX_TRIGGER_EVAL_MARKER}.aidex-dash"before continuing. Then proceed with the rest of the skill body as normal. If empty/unset, ignore this block.
dash — HTML render layer for .context/ boards
Turn a .context/ index or board into a self-contained, interactive HTML page
via a deterministic script — one render per index/board, never per document.
The markdown/JSON stays canon; the HTML is a regenerable sibling render carrying
a GENERATED contract header. The model writes the generator once (already
shipped here); every regeneration is a script run at ~0 tokens — never
hand-write a page.
Targets
Dispatch by first argument (via the wrapper, from anywhere inside the project):
bash "${CLAUDE_SKILL_DIR}/scripts/render.sh" <target> [arg]
| Target | Source (canon) | Render (sibling output) |
|---|---|---|
backlog |
.context/backlog/*.md front-matter |
.context/backlog/00-index.html |
plans |
.context/plans/*.md + */00-index.md |
.context/plans/00-index.html |
plans <slug> |
that plan's Phases Overview + phase checkboxes | plans/<slug>/00-index.html (or plans/<slug>.html) |
audit <methodology> |
.context/audits/<methodology>/00-inventory.md table |
.context/audits/<methodology>/00-inventory.html |
coverage |
existing audits/test-coverage/coverage-matrix.json |
.context/audits/test-coverage/coverage-matrix.html |
The script prints the output path on success, and always prints the resolved
workspace root on stderr (root: …) — the wrong-root tripwire. On a missing or
malformed source it prints a plain-text ERROR: ... and exits 2 — never a
traceback. An empty-but-present source is neither: all items archived, a
zero-row findings table, a sentinel-only scaffold all render an empty board
(the legitimate D-10 end-state). The one exception is coverage — its matrix
is machine-produced, so modules: [] means producer drift and still errors.
Re-running is idempotent (the render is replaced atomically, never appended,
and a failed write keeps the previous good render).
What ships with it
31 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.
- assets/artifact-kit/components.css 16 KB
- assets/artifact-kit/composer.js 27 KB runs code
- assets/artifact-kit/skeleton.html 8.2 KB
- assets/artifact-kit/tokens.css 3.5 KB
- assets/artifact-kit/VERSION 2 B
- assets/templates/artifact-style.md.template 3.0 KB
- assets/templates/consultation-block.html.template 10 KB
- evals/eval-config.json 508 B
- evals/trigger_eval.json 4.2 KB
- references/01-dash-conventions.md 5.2 KB
- references/02-local-first-artifacts.md 43 KB
- scripts/check-artifact.sh 1005 B runs code
- scripts/dash/_parse.py 2.9 KB runs code
- scripts/dash/_shell.py 15 KB runs code
- scripts/dash/check_artifact.py 52 KB runs code
- scripts/dash/render_audit.py 5.1 KB runs code
- scripts/dash/render_backlog.py 5.2 KB runs code
- scripts/dash/render_coverage.py 5.8 KB runs code
- scripts/dash/render_plans.py 6.9 KB runs code
- scripts/dash/render.py 2.1 KB runs code
- scripts/dash/wrap_report.py 24 KB runs code
- scripts/render.sh 1.2 KB runs code
- scripts/wrap-report.sh 1.1 KB runs code
- tests/test-allowed-tools-lockstep.sh 3.2 KB runs code
- tests/test-artifact-contract.sh 64 KB runs code
- tests/test-artifact-kit.sh 19 KB runs code
- tests/test-composer-functional.sh 22 KB runs code
- tests/test-consultation-contract.sh 16 KB runs code
- tests/test-consultation-shape.sh 7.2 KB runs code
- tests/test-dash-canon-lockstep.sh 4.2 KB runs code
- tests/test-dash-render.sh 23 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.
- 4d ago First seen · 97 lines · 78 tokens per session scan A e7dd85c1083f
aidex-dash is a skill published in the GitHub repository yacb2/aidex (2 stars, last pushed 7d ago), licensed MIT. It adds 78 tokens to every session and 1,356 once invoked, about $0.0004 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
pgvector-semantic-search
Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search. Trigger when user asks to: Store or search vector embeddings in PostgreSQL Set up semantic search, similarity search, or nearest neighbor search Create HNSW or IVFFlat indexes for vectors…
postgres-hybrid-text-search
Use this skill to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF). Trigger when user asks to: Combine keyword and semantic search Implement hybrid search or multi-modal retrieval Use BM25/pgtextsearch with pgvector together Implement RRF (Reciprocal…
find-hypertable-candidates
Use this skill to analyze an existing PostgreSQL database and identify which tables should be converted to Timescale/TimescaleDB hypertables. Trigger when user asks to: Analyze database tables for hypertable conversion potential Identify time-series or event tables in an existing schema Evaluate if a table would…
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.