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 efficiency-auditgit 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/efficiency-audit)<a href="https://agentmods.dev/skills/arozumenko/sdlc-skills/efficiency-audit"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/efficiency-audit/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/efficiency-audit"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/efficiency-audit.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 | $0.00095 | $0.07634 |
| Opus 5 | $0.00048 | $0.03817 |
| Sonnet 5 | $0.00019 | $0.01527 |
| Haiku 4.5 | $0.00010 | $0.00763 |
Grade B, and why
efficiency-audit scanned grade B with 1 finding 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 9d 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.
Tells the agent never to refusemediumAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
| The user wants the rollup's questions answered | They often don't. `--json` gives you the per-unit ledger — role, model, tokens, branch, timestamps, tool calls — and any question you can answer by grouping it is fair g Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 494 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Efficiency Audit
Hosts & data sources
- Claude Code — reads transcripts under
$CLAUDE_CONFIG_DIR/projects(else~/.claude/projects,~/.config/claude/projects) and prices every dollar withccusage(auto-run vianpx ccusage@latest). - GitHub Copilot CLI —
--host copilotreads~/.copilot/session-state/*/events.jsonl(also$COPILOT_HOMEand a repo-local./.copilot; all existing roots are searched), needs no ccusage, and takes cost from Copilot's own billed figure (session.shutdown.totalNanoAiu, AI credits at $0.01 each). Parent-session roles come from thesubagent.selectedevent (CLI ≥1.0.63; older streams report role-less sessions), loaded skills fromskill.invoked. Sessions predating GitHub's 2026-06-01 usage-based billing carry no credit figure and report tokens with cost n/a. This store is CLI-only — VS Code Copilot sidebar sessions live in VS Code's own workspaceStorage and are covered by thetokenomicsskill's ledger, not by this audit. build-report-html.mjsrenders either host's--jsonsnapshot as one self-contained HTML page.--resolved-fromworks on both hosts and needs no workflow: it reads the pipeline's.agents/automation/<slug>/report.json, whether written by the batch workflow or by the lead at close (including after rebuilding an interrupted run).
Answer "what did this cost, and who spent it" for AI coding-agent work —
down to the individual sub-agent — with ccusage as the single source of every
dollar. This skill never prices tokens itself: no pricing table, no estimate.
What it adds on top of ccusage is the join ccusage can't do alone — attaching
each metered dollar to the role / session / day / project that spent it.
(The markdown report shows totals, by-role, and by-day; the per-project
breakdown, byProject, is in the --json output only.)
Alongside cost, it reports activity metrics read from the same transcripts,
per role and per unit: tool calls (total + errored, with a success rate),
skills loaded (count + names), tokens (with cache-hit rate + output
share), time (active-minutes + wall-clock span), and sub-agents
dispatched (count + names, via the Agent tool). Counts are in the markdown;
full per-unit names/detail are in the --json ledger (skills, dispatched,
toolCalls, toolErrors, models, agentMinutes, wallClockMin,
startedAt, endedAt).
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.
- README.md 9.7 KB
- references/methodology.md 16 KB
- scripts/build-report-html.mjs 22 KB runs code
- scripts/build-report-html.test.mjs 9.8 KB runs code
- scripts/copilot-usage.mjs 18 KB runs code
- scripts/copilot-usage.test.mjs 18 KB runs code
- scripts/run-reports.mjs 16 KB runs code
- scripts/run-reports.test.mjs 15 KB runs code
- scripts/usage-rollup.mjs 69 KB runs code
- scripts/usage-rollup.test.mjs 33 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.
- 9d ago First seen · 494 lines · 95 tokens per session scan B 9b0614b9a556
efficiency-audit is a skill published in the GitHub repository arozumenko/sdlc-skills (20 stars, last pushed 5d ago), licensed MIT. It adds 95 tokens to every session and 7,634 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…