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 bdfinst/agentic-dev-team --skill context-loading-protocolgit clone --depth 1 https://github.com/bdfinst/agentic-dev-teamWrote 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/bdfinst/agentic-dev-team/context-loading-protocol)<a href="https://agentmods.dev/skills/bdfinst/agentic-dev-team/context-loading-protocol"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/context-loading-protocol/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/bdfinst/agentic-dev-team/context-loading-protocol"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/context-loading-protocol.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 148 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00048 | $0.01752 |
| Opus 5.5 | $0.00019 | $0.00701 |
| Sonnet 5.5 | $0.00010 | $0.00350 |
| Haiku 4.5 | $0.00005 | $0.00175 |
Grade A, and why
context-loading-protocol 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 17d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Loading Protocol
Token-budget reference (CLAUDE.md baseline, full-load ceiling, per-agent and per-skill costs) is the Baseline Budget section of CLAUDE.md. This skill is the runtime procedure; don't duplicate the table here — it goes stale.
Constraints
- Never load all agents upfront; load only the primary agent for each phase.
- Keep total context below 40% of the model's window at all times.
- Load agents on demand when their phase begins, not speculatively.
- Use tool-based file reads (Read); do not paste file contents into the prompt.
Enforcement
No hook blocks or warns on capability loads any more (the former context
ceiling hook was removed; see ADR 0043).
The harness compacts the conversation itself at the percentage
/dev-team:setup writes to the repo's .claude/settings.json
(CLAUDE_AUTOCOMPACT_PCT_OVERRIDE, default 40). Repos that never ran /setup
keep the harness default, which is much later, and get a one-line advisory at
session start. After a compaction, a compact SessionStart hook re-injects
the active /build phase, step and plan progress.
So the budget estimate below is the planning tool you apply before loading,
and /handoff is yours to run by hand when a deliberate, structured summary
is worth more than a generic compaction.
Why 40%
The 40% default is a conservative planning target, not a claimed accuracy cliff. Chroma's Context Rot study found degradation across 18 models (including Claude 4) is gradual, not a sharp drop at any single percentage. Needle-in-a-haystack benchmarks like RULER and NoLiMa show a model's effective context is often only about half its advertised window, with sharp accuracy drops on non-lexical retrieval well before the window limit. Anthropic's effective context engineering guidance recommends proactive compaction well ahead of the limit. Given that evidence, budgeting to 40% of the window leaves headroom before quality degrades, rather than chasing a precise threshold that doesn't exist. There is no absolute token cap: the percentage applies to the window, so 40% of a 1M window is 400K.
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.
- 17d ago Changed · -49 lines 2312e238fd5d
- 1mo ago First seen · 207 lines · 48 tokens per session scan A ac3b469a5028
context-loading-protocol is a skill published in the GitHub repository bdfinst/agentic-dev-team (295 stars, last pushed 4d ago), licensed MIT. It adds 48 tokens to every session and 1,752 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 2026-09-03.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…