What is token-efficiency?

A shared set of rules for managing an agent's working context, including which sources to trust, how much code to read, and when to stop investigating.

Use it at the start of coding tasks and reviews to guide context selection, confidence checks, and response length.

It limits unnecessary reading and keeps reviews and implementation work focused and concise.

token-efficiency — Skill for Claude Code by saeedkolivand

Install

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.

Any agent

npx skills add saeedkolivand/ai-job-hunter-app --skill token-efficiency

Clone the repo

git clone --depth 1 https://github.com/saeedkolivand/ai-job-hunter-app

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/saeedkolivand/ai-job-hunter-app/token-efficiency/github.svg)](https://agentmods.dev/skills/saeedkolivand/ai-job-hunter-app/token-efficiency)

Your own site

<a href="https://agentmods.dev/skills/saeedkolivand/ai-job-hunter-app/token-efficiency"><img src="https://agentmods.dev/badge/skills/saeedkolivand/ai-job-hunter-app/token-efficiency/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/saeedkolivand/ai-job-hunter-app/token-efficiency"><img src="https://agentmods.dev/badge/skills/saeedkolivand/ai-job-hunter-app/token-efficiency.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 687 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00687
Opus 5	$0.00021	$0.00344
Sonnet 5	$0.00008	$0.00137
Haiku 4.5	$0.00004	$0.00069

Measured 9d ago against content hash f40e76e60448, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

token-efficiency 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 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.

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.

.claude/skills/token-efficiency/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Token-efficiency contract (all agents)

Context-source priority (in order)

codegraph (structural) — symbols/calls/impact: MCP codegraph_explore when your allowlist has it, else CLI codegraph callers/callees/impact/query.
graphify (semantic) — meaning/rationale/cross-doc: MCP query_graph/shortest_path/get_* when connected, else CLI graphify query|explain|path.
source — authoritative for any region edited this turn.
docs/knowledge/ — contracts, standards.
lessons — on-demand only, never bulk-loaded.

Read discipline

Minimum files; no repo-wide scans — codegraph for "where/what calls X", graphify for "what connects to X", rg only when neither answers.
Stop at ~90% confidence. Read the relevant section, not the whole file.

Severity rubric (anchors blocking — STRICT MODE, verify-don't-assume)

CRITICAL — exploitable security on a secret/credential/IPC/updater/network-egress path; data loss/corruption; breaks a release or CI gate.
HIGH — architecture-rule violation (std::env::var outside platform/, reqwest::Client outside net/, untyped Result<_,String> outside error/); changed non-trivial logic WITHOUT a test, or a weak/tautological/mock-asserting test; untested error/edge/security path on changed code; provider-specific coupling in business logic; PII/temp-file-cleanup/retention regression; user-facing text whose i18n key is missing from en or de.
MEDIUM — unguarded hot-path perf regression, non-blocking correctness smell, missing non-critical edge test.
LOW — style/naming/comments/formatting/docs.
Only HIGH/CRITICAL block. Tie-break: round UP for test-coverage, error/edge-path, i18n, security, and data findings; round down only for pure style/docs. Confirm every claim against the real code/files; never pass a hunk you did not actually read.

Output format

Terse findings only: SEVERITY · file:line · finding · one-line fix. No prose essays.

Strict enforcement (canonical — agent files point here, never restate)

Read the full file on GitHub · 40 lines

Changes

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 · 40 lines · 42 tokens per session scan A f40e76e60448

Subscribe to this mod's changes

token-efficiency is a skill published in the GitHub repository saeedkolivand/ai-job-hunter-app (55 stars, last pushed yesterday), licensed Apache-2.0. It adds 42 tokens to every session and 687 once invoked, about $0.0002 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 2026-09-03.

Building agents React Rust ai job-search resume-builder tauri

anarlog

Query Anarlog meetings, notes, summaries, transcripts, participants, action items, and recurring history. Use when a user asks about their Anarlog meeting data or needs meeting context for another task.

fastrepl/anarlog · 44 tokens

resume-builder

Generate professional resumes that conform to the Reactive Resume schema. Use when the user wants to create, build, or generate a resume through conversational AI, or asks about resume structure, sections, or content. This skill guides the agent to ask clarifying questions, avoid hallucination, and produce valid JSON…

amruthpillai/reactive-resume · 71 tokens

json-ui

CRITICAL: Use for json-ui component rendering and development. Triggers on: json-ui, json render, component catalog, report render, HTML report, I18nString, i18n, bilingual, language switch, dual language, PaperHeader, AuthorList, Abstract, MetricsGrid, Section, Highlight, Zod schema, catalog.ts, cli.ts…

actionbook/actionbook · 118 tokens

token-efficiency