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 paruff/uFawkesAI --skill token-budgetgit clone --depth 1 https://github.com/paruff/uFawkesAIWrote 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/paruff/ufawkesai/token-budget)<a href="https://agentmods.dev/skills/paruff/ufawkesai/token-budget"><img src="https://agentmods.dev/badge/skills/paruff/ufawkesai/token-budget/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/paruff/ufawkesai/token-budget"><img src="https://agentmods.dev/badge/skills/paruff/ufawkesai/token-budget.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 | $0.00035 | $0.00832 |
| Opus 5 | $0.00017 | $0.00416 |
| Sonnet 5 | $0.00007 | $0.00166 |
| Haiku 4.5 | $0.00003 | $0.00083 |
Grade A, and why
token-budget 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 6d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Token Budget
Load trigger:
"load token-budget skill"> DORA: Cap 3 (Context Engineering) Token cost: Low (meta: about token cost itself)
Purpose
Audit and manage the token footprint of agent sessions to stay within AGENTS.md §4 budget protocols and avoid runaway Copilot billing.
Token Cost Tiers (approximate — verify with current billing)
| Tier | Use | Context size |
|---|---|---|
| Low | Routing, quick lookups, preflight | < 8K tokens |
| Medium | Feature implementation, docs | 8K–20K tokens |
| High | Complex refactors, full file rewrites | 20K–32K tokens |
| Over-budget | Multi-file architectural changes | > 32K tokens |
Note: these are approximate estimates. Actual token counts depend on model, context management, and billing plan. Verify current rates at github.com/features/copilot and anthropic.com/pricing before planning large agent workloads.
Context Footprint Sources (in descending size order)
- AGENTS.md (always-on) — target: ≤ 88 lines ≈ ~2K tokens
- Loaded skill files — each ≈ 500–800 tokens
- Files read from context index — varies by file size
- Conversation history — grows each turn
- PR diff being reviewed — varies
Audit Protocol
Before a long session, estimate context size:
# Count lines in always-on context
wc -l AGENTS.md .agents/README.md
# Estimate token count (rough: 1 line ≈ 20–25 tokens)
echo "Estimated always-on tokens: $(($(wc -l < AGENTS.md) * 25))"
# Check which skills are loaded in this session
# (manual tracking — list them here)
Cost Control Strategies
Strategy 1 — Keep AGENTS.md lean Every line added to AGENTS.md costs tokens on every agent turn. The 88-line target is a billing control, not just an aesthetic preference. Offload project-specific details to skill files loaded on demand.
Strategy 2 — Scope context files
Do not read entire files when only a section is needed.
Instruct agents: "Read only the services/ section of AGENTS.md §3"
rather than loading the full context index.
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.
- 6d ago First seen · 95 lines · 35 tokens per session scan A 1011b6013952
token-budget is a skill published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed 17d ago), licensed MIT. It adds 35 tokens to every session and 832 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.
Other skills, from other repositories
planning-with-files
Persistent file-based planning for multi-step AI-agent work. Keeps taskplan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and…
infrastructure-tools
Skill for the tools module — discovery, validation, scope, and private-sidecar symlink sync for the top-level tools/ directory (executable entry points such as scripts, skills, and agents stored as passive manifests with scripts/ directories). Use when discovering tools (discovertools), resolving a tool path…
template-maintenance
On-demand maintenance helpers for the template repository. Includes workspace management, project info display, working-project rendering, PDF re-rendering, executive output organization, test supplement merging, batch source improvement, pre-commit setup, and CodeGraph index helpers. None run in the default pipeline…
concierge
Use when a task needs the judgment of a Concierge — securing a reservation at a fully-booked restaurant or sold-out venue, coordinating a multi-vendor guest request (dinner, transportation, and a gift delivery) inside a tight window, deciding when to pivot from a failed Plan A to a same-caliber Plan B, or navigating a…
correspondence-clerk
Use when a task needs the judgment of a Correspondence Clerk — selecting and customizing a template response to a standardized written inquiry, triaging a correspondence queue against SLA deadlines, deciding when a form letter suffices versus needs escalation, or auditing a response-template library for staleness.
open-loops
A conversation-audit skill for finding unresolved points in a long chat. It checks whether questions, suggestions, decisions, or needed clarifications were left without a clear response.