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 commands/vladm3105/aidoc-flow-framework/nextgit clone --depth 1 https://github.com/vladm3105/aidoc-flow-frameworkWhat 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 | $0.00023 | $0.00740 |
| Opus 5 | $0.00012 | $0.00370 |
| Sonnet 5 | $0.00005 | $0.00148 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade A, and why
next 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Next
Tell the user the one thing to do next. Not a menu, not the whole roadmap —
one concrete command. Uses the same detection logic as /aidoc-flow:status,
applies a small decision tree, and emits a single recommendation.
Instructions
-
Resolve project root and detect layer state — identical to step 1-2 of
/aidoc-flow:status. Skip the table render; you only need the per-layer(exists, instances, audited)triple. -
Apply the decision tree in order; first matching rule wins:
Rule Condition Recommend R0 No layer directories exist at all /aidoc-flow:project-init— scaffold the SDD layoutR1 A layer exists but the layer below it (smaller N) does NOT — out-of-order/aidoc-flow:doc-flow— out-of-order layers detected; this skill explains the canonical orderR2 The lowest-numbered missing layer is Nand layerN-1exists/aidoc-flow:doc-<layer N>-autopilot— draft layerNfrom the upstream artifactR3 Every layer present has an audit, and IPLAN exists with audit "All eight layers are present and audited. The next step is implementation — drive the IPLAN to code." R4 At least one layer exists without an audit (the lowest such) /aidoc-flow:doc-<that layer>-audit— score the layer before promotingR5 A layer's most recent audit scores below its gate (only knowable if .aidoc/carries that info)/aidoc-flow:doc-<that layer>-fixer— remediate the audit findingsIf a rule needs information you cannot resolve (e.g. R5 requires gate scores you cannot read), skip to the next rule.
-
Render the recommendation — one block, three lines:
Position: <Highest layer present> (<N> of 8) Next: <one of the recommendations above> Why: <one sentence explaining the rule that fired>Example:
Position: PRD (2 of 8) Next: /aidoc-flow:doc-ears-autopilot Why: PRD exists; EARS (the next layer) does not.
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 · 67 lines · 23 tokens per session scan A 2a271073bb00
next is a command published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 740 once invoked, about $0.0001 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 commands, from other repositories
pr-address
Address PR review comments on current branch.
enforce_standards
CRITICAL: Before running the code standards enforcer, we must prepare the stack properly and abort if there are merge conflicts.
validate_changed_docstrings
Validates Python docstrings in all uncommitted changed files using Sphinx parsing.
OPSX: Continue
Continue working on a change - create the next artifact (Experimental).
OPSX: Propose
Propose a new change - create it and generate all artifacts in one step.
spec-research
需求 → 约束集(并行探索 + OPSX 提案).