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 skills add vladm3105/aidoc-flow-framework --skill sdd-iplangit clone --depth 1 https://github.com/vladm3105/aidoc-flow-frameworkWrote 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/vladm3105/aidoc-flow-framework/sdd-iplan)<a href="https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/sdd-iplan"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/sdd-iplan/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/sdd-iplan"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/sdd-iplan.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00042 | $0.00454 |
| Opus 5.5 | $0.00017 | $0.00182 |
| Sonnet 5.5 | $0.00008 | $0.00091 |
| Haiku 4.5 | $0.00004 | $0.00045 |
Grade A, and why
sdd-iplan 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 19d 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.
What it actually says
SDD IPLAN Author
Framework skill — routes to
framework/layers/08_IPLAN/IPLAN-TEMPLATE.yamland the executing exampleframework/archive/CHG-*/IPLAN-*.yaml. Paths below use<skills-root>= thisframework/skills/directory. The authorizing CHG (sdd-chg-author) must exist first, except for seed-phase drafting before the first BRD — the sole change needing neither object.
1. The gate (non-negotiable)
No code may be written without an IPLAN, and the IPLAN must be In Progress,
reference its authorizing CHG (source_chg), and list every modified file in
file_manifest — one entry per path with action (create/modify) and
status (TODO → DONE). A manifest that misses a file the diff touches fails
the gate the same way a missing IPLAN does.
2. Shape follows the flow
Match the IPLAN shape to the classified flow: DIR2C takes a scoped IPLAN
(manifest + steps + rollback only); CODE2C takes a bugfix-subtype IPLAN
(parent_iplan + source_chg, repair-scoped manifest, rollback); full
flows take the full form with all code steps and the complete manifest.
Bug fixes ride their IPLAN's authorizing CHG when it is active, otherwise
the bugfix vehicle (C1 CHG + bugfix IPLAN, parent standing).
3. Execute and close out
Work the manifest TODO → DONE, keeping phase_findings honest (guards
observed red, fixes declined with reasons). Verification commands named in
the IPLAN run per step, not once at the end. Flip status to Implemented
only when the manifest is fully DONE and the suites are green on the head
that carries the work.
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.
- 19d ago First seen · 40 lines · 42 tokens per session scan A ed8a7511773c
sdd-iplan is a skill published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed 5d ago), licensed MIT. It adds 42 tokens to every session and 454 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-26.
sdd-iplan compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sdd-iplanvladm3105/aidoc-flow-framework | Skill | 17 | 5d ago | MIT | A | 42 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | 7d ago | MIT | A | 200 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |