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 arozumenko/sdlc-skills --skill risk-registergit clone --depth 1 https://github.com/arozumenko/sdlc-skillsWrote 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/arozumenko/sdlc-skills/risk-register)<a href="https://agentmods.dev/skills/arozumenko/sdlc-skills/risk-register"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/risk-register/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/arozumenko/sdlc-skills/risk-register"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/risk-register.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 | $0.00041 | $0.01773 |
| Opus 5.5 | $0.00016 | $0.00709 |
| Sonnet 5.5 | $0.00008 | $0.00355 |
| Haiku 4.5 | $0.00004 | $0.00177 |
Grade A, and why
risk-register 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 1mo 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Risk register
One append-only log, .agents/security-testing/register/events.jsonl,
rows R-nnnn. Every command re-folds the whole log through
lib/transitions.mjs's closed table and appends at most one line; a
(event, from) pair outside the table is refused, nothing is written.
A row
{"id": "R-0001", "finding_id": "<64-hex sha256>", "title": "…",
"priority": "p1", "status": "open", "owner": "…", "ticket_url": "",
"accepted_until": "", "approvals": [], "superseded_by": ""}
status is one of open, fixed, regressed, accepted,
false-positive, superseded. approvals is append-only — every
accept, revoke and close-false-positive event pushes one record
onto it; nothing is ever removed from it. accepted_until is cleared
on every transition that leaves accepted (including supersede).
The ten events, from → to
add: no row →open—--finding <64-hex sha256> --priority <p0..p3> --title "<t>" [--owner <o>]; setsfinding_id,title,priority,owner. You run it.accept:open→accepted,regressed→accepted— appends an approval record toapprovalsand setsaccepted_until. You run it.revoke:accepted→open— appends an approval record;accepted_untilis cleared. You run it.acceptance-expired:accepted→open— fired byregister.mjs checkfor every accepted row whoseaccepted_untilis strictly before today (UTC); the acceptance still stands on that day itself and lapses at 00:00 UTC the next day.accepted_untilis cleared. Emitter-only.fixed:open→fixed,regressed→fixed,accepted→fixed— fired byverify.mjs'sVERIFIEDverdict;accepted_untilis cleared if the row wasaccepted. Emitter-only.regressed:fixed→regressed— fired byverify.mjs'sREGRESSEDverdict; only afixedrow can regress. Emitter-only.close-false-positive:open→false-positive,regressed→false-positive— appends an approval record. You run it.reopen:fixed→open,false-positive→open— status only; the priorclose-false-positiverecord stays inapprovals' history, it is not erased. You run it.supersede:open→superseded,fixed→superseded,regressed→superseded,accepted→superseded— setssuperseded_by;accepted_untilis cleared if the row wasaccepted. You run it.ticket:open→ same,fixed→ same,regressed→ same,accepted→ same (status unchanged) — setsticket_url. You run it. Threats are not ticketed in v1:ticketis for finding rows.
What ships with it
10 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.
- references/approvals.md 4.5 KB
- references/transitions.md 4.9 KB
- scripts/lib/cli.mjs 4.4 KB runs code
- scripts/lib/engagement.mjs 4.9 KB runs code
- scripts/lib/redact.mjs 3.4 KB runs code
- scripts/lib/redaction-rules.json 1.1 KB
- scripts/lib/transitions.mjs 7.9 KB runs code
- scripts/lib/transitions.test.mjs 7.1 KB runs code
- scripts/register.mjs 23 KB runs code
- scripts/register.test.mjs 22 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.
- 1mo ago First seen · 150 lines · 41 tokens per session scan A 87125e17921a
risk-register is a skill published in the GitHub repository arozumenko/sdlc-skills (25 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 1,773 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 2026-09-19.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.