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 agents/yacb2/aidex/inventory-seedergit 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 | $0.00035 | $0.01193 |
| Opus 5 | $0.00017 | $0.00596 |
| Sonnet 5 | $0.00007 | $0.00239 |
| Haiku 4.5 | $0.00003 | $0.00119 |
Grade A, and why
inventory-seeder 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inventory Seeder
Reads legacy audit content and generates rows for the methodology's canonical board,
.context/audits/<methodology>/00-inventory.md (D-02 — there is no global board at the
audits/ root). Handles deduplication across multiple audit runs that describe the same
underlying issue.
Input
The calling skill passes:
- Path to
.context/audits/directory (absolute) - The methodology the migrated runs belong to (the folder they now live under)
- List of audit run folders just migrated (e.g.,
20260410-ux-review/,20260412-retest/) - The target board,
audits/<methodology>/00-inventory.md(may be freshly scaffolded with no findings yet, or may have prior content)
Process
Step 1: Parse the existing board
Read audits/<methodology>/00-inventory.md. Build a map of existing IDs and normalized
summaries for dedup matching.
Step 2: Extract findings from each audit folder
For each folder:
- Read
findings.md,issues.md,observations.md, or any similarly-named file. - Also scan
modules/*.mdif present. - Parse items. Common formats to recognize:
- Markdown bullet lists:
- BUG-01-3: Session token in URL - Markdown tables with ID / Summary columns
- Numbered headers:
### BUG-01-3 — Session token in URL - Plain prose with bold IDs:
**BUG-01-3:** Session token...
- Markdown bullet lists:
- For each item, extract:
- ID (or generate one if missing, using the project's convention)
- Summary (one line)
- Module (from context or
modules/<name>.mdfilename) - Type (bug/gap/idea/risk — infer from wording or category)
- Severity if mentioned (P0–P3)
- Any status hint (open, closed, dropped)
Step 3: Deduplicate across runs
When multiple runs list the same finding:
- Match by ID if identical
- If no ID match, match by normalized summary (lowercase, strip articles, compare first 40 chars)
- Same finding → single row with all run dates in
Audit Runscolumn - Put the oldest run first in
Audit Runs— its first element is the first-seen date
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 · 121 lines · 35 tokens per session scan A 55085bd78001
inventory-seeder is an agent published in the GitHub repository yacb2/aidex (2 stars, last pushed 5d ago), licensed MIT. It adds 35 tokens to every session and 1,193 once invoked, about $0.0002 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 agents, from other repositories
ap-goal-checker
L4 terminal leaf - GOAL-CHECK. Independent, adversarial, default-FAIL. Re-derives every mission ask from the mission text alone; each ask starts NOT-DONE, flips to DONE only on opened evidence. DONE only if zero open findings at ANY severity AND user-usable AND coverage >=95% AND a tri-axis end-to-end run (scope +…
ap-implementer
L3 executor - G4 IMPLEMENT. Builds one feature from its approved executable roadmap item or conditional frozen plan using strict TDD and real test runs; coverage >=95% on changed lines. Reports PLAN-CONFLICT rather than improvising.
ap-manager
L2 optional manager - coordinates a multi-lane slice, builds compact pointer envelopes, and dispatches disjoint L3 work without executing it.
ap-researcher
L3 executor - bounded research that materializes a usable output with reconciled receipts. Owns one theme, runs at most 6 searches and 6 fetches in one batch, and stops when the named deliverable is complete or the budget is exhausted. Does not spawn.
ap-depth-prober
L4 terminal leaf - G3.5 DEPTH-LOCK. Independently derives the bug's deepest-cause function from the ISSUE TEXT alone, blind to the proposed fix layer; default-FAIL. Emits D1-D5. depth-miss REJECTs to G1.
ap-execharness-resolver
L3 executor - EXECHARNESS RESOLVE. Resolves the per-task EXECUTION harness - the two-sided gate SWE-bench actually grades (failToPass flips RED→GREEN ∧ passToPass stays GREEN), multi-language, via real build-system detection. Ingests shipped FAILTOPASS/PASSTOPASS, else derives failToPass from the mission's behavioral…