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 Eliyce/paqad-ai --skill context-budget-plannergit clone --depth 1 https://github.com/Eliyce/paqad-aiWrote 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/eliyce/paqad-ai/context-budget-planner)<a href="https://agentmods.dev/skills/eliyce/paqad-ai/context-budget-planner"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/context-budget-planner/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/eliyce/paqad-ai/context-budget-planner"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/context-budget-planner.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 | $0.00029 | $0.00787 |
| Opus 5 | $0.00015 | $0.00394 |
| Sonnet 5 | $0.00006 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00079 |
Grade A, and why
context-budget-planner 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 11d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What It Does
Predicts the token footprint of the upcoming implementation phase before it starts. Reads spec size, test plan size, affected module docs, and known changed files; sums their token cost using the per-line weights in the heuristics reference; compares against the available budget; and recommends compaction when the estimate would push the session into the Amber or Red tier.
The point is to catch starvation before it happens, not after compaction has already evicted decisions mid-task.
Use This When
Use this once at the boundary between planning and implementation in the graduated and full lanes — after acceptance criteria and test plan exist, before the first source file is opened. Skip in the fast lane; the overhead is not justified for low-complexity work.
Inputs
- Read the active spec at
spec_pathfirst. - Read
test_plan_pathwhen supplied. - Read each module doc in
affected_module_doc_pathsonly enough to compute its line count. - Read
references/budget-heuristics.mdbefore applying any threshold so the per-line weights and tier boundaries stay consistent across runs.
Procedure
- Determine the project's model context window (from project profile) and committed tokens (default 200000 / 30000 if not declared).
- Pick per-line weights from
references/budget-heuristics.md(orassets/weights.default.txtif the project has none yet). - Pipe
<weight> <path>rows intoscripts/estimate-tokens.sh --available <N> --committed <N>— it line-counts, multiplies, sums, picks the tier, and emits the markdown block. - When the script reports Amber or Red, fill the compaction list using the priority order from
references/budget-heuristics.md. - Validate the final output with
scripts/lint-output.sh.
Output Contract
- Match
assets/output.template.md:## Context Budget, singleSummary:line,### Per-Artifact Estimatetable,### Recommended Compactions. - Green/Yellow →
Recommended Compactions: noneexactly. Amber/Red → ordered list with one-line reasons. - Output must pass
scripts/lint-output.sh(exit 0).
What ships with it
6 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.
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.
- 11d ago First seen · 76 lines · 29 tokens per session scan A 4e7c0307f277
context-budget-planner is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 787 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
pr-writing-review
Extract and analyze writing improvements from GitHub PR review comments. Use when asked to show review feedback, style changes, or editorial improvements from a GitHub pull request URL. Handles both explicit suggestions and plain text feedback. Produces structured output comparing original phrasing with reviewer…
session-investigator
Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…
auto-go
A command that implements code from a SPEC, a document describing the required behavior and work.
auto-plan
A code-planning skill that examines a codebase and creates a detailed specification, implementation plan, and acceptance criteria. It can organize requirements using EARS, a structured way to describe how software should behave in different situations.
agent-pipeline
Multi-agent pipeline orchestration skill.
adaptive-quality
Per-task execution profile selection based on complexity in Balanced quality mode.