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-chg-triagegit 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-chg-triage)<a href="https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/sdd-chg-triage"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/sdd-chg-triage/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-chg-triage"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/sdd-chg-triage.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 | $0.00048 | $0.00517 |
| Opus 5.5 | $0.00019 | $0.00207 |
| Sonnet 5.5 | $0.00010 | $0.00103 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
sdd-chg-triage 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 CHG Triage (Pre-Implementation Validation)
Framework skill — the engine-agnostic half of issue validation. For the repo-specific workflow (labels, triage notes, memory write-back), dispatch the local
aidoc-triageskill alongside this one. Paths below use<skills-root>= thisframework/skills/directory.
Triage answers "may I implement now" (go/no-go). It NEVER implements, closes, or rewrites history.
1. Fetch live, read the whole thread
gh issue view <N> with state, labels, body, and every comment, oldest
first. Corrections inside the thread supersede the body — triage the
corrected claim and name what it superseded. Filed line numbers rot fast:
treat them as hints, never facts.
2. Verify each claim against the tree
For every load-bearing claim, run the check: file and line exist (grep -n,
git log --oneline -3 -- <file>), counts reproduced by re-measuring (record
when a recount corrects the filing), CI behavior read from gh pr checks /
gh run view --log-failed. "Never held" claims need full-history
enumeration, not a spot check.
3. Supersede scan, then verdict
Search later framework/archive/CHG-*/, decisions, merged PRs, and open
branches for anything that already fixed, scoped, or declined the claim —
name links or record "none found", never assume. Exactly one verdict:
GO (all load-bearing claims alive, no superseder), SCOPED-GO (name the
surviving subset; the rest is not authorized), STALE, SUPERSEDED, or
ALREADY-FIXED. On the last three, report with evidence and stop — do not
open a vehicle around the verdict.
4. Hand off
On GO, classify with sdd-chg-flow and re-check blast radius against the
current tree (the filing-time radius may have shifted). The verdict is
perishable: record the dev SHA it was verified against.
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 · 47 lines · 48 tokens per session scan A ab985a1865f6
sdd-chg-triage is a skill published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed 5d ago), licensed MIT. It adds 48 tokens to every session and 517 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-chg-triage compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sdd-chg-triagevladm3105/aidoc-flow-framework | Skill | 17 | 5d ago | MIT | A | 48 | Claude Code, Codex |
| systematic-debuggingopen-metadata/OpenMetadata | Skill | 16k | today | Apache-2.0 | A | 37 | Claude Code |
| log-error-digestzebbern/claude-code-guide | Skill | 4.7k | yesterday | MIT | A | 71 | Claude Code, Codex |
| cwv-optimizeradobe/skills | Skill | 326 | today | Apache-2.0 | A | 112 | Claude Code |
| ci-fixersipyourdrink-ltd/bernstein | Skill | 1.2k | today | Apache-2.0 | A | 15 | Claude Code, Codex |
| self-healhristo2612/jinn | Skill | 329 | yesterday | MIT | A | 19 | Claude Code, Codex |
| diagnosing-missing-recordingsPostHog/posthog | Skill | 41k | today | none | A | 76 | Claude Code, Codex |