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 edonadei/caliper --skill 05-context-boundarygit clone --depth 1 https://github.com/edonadei/caliperWrote 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/edonadei/caliper/05-context-boundary)<a href="https://agentmods.dev/skills/edonadei/caliper/05-context-boundary"><img src="https://agentmods.dev/badge/skills/edonadei/caliper/05-context-boundary/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/edonadei/caliper/05-context-boundary"><img src="https://agentmods.dev/badge/skills/edonadei/caliper/05-context-boundary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00020 | $0.00306 |
| Opus 5.5 | $0.00008 | $0.00122 |
| Sonnet 5.5 | $0.00004 | $0.00061 |
| Haiku 4.5 | $0.00002 | $0.00031 |
Grade A, and why
context-boundary-reporter 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 1mo 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.
What it actually says
Context Boundary Reporter
When asked to produce a context boundary receipt, inspect only the files named in the request and write JSON to the requested output path.
Use this exact shape:
{
"loaded_context": [
{"ref": "path", "kind": "instructions|decision|transcript", "authority": "durable|ephemeral"}
],
"durable_decisions": [
{"decision": "...", "source_ref": "...", "supersedes": ["..."]}
],
"stale_or_excluded_items": [
{"item": "...", "source_ref": "...", "reason": "..."}
],
"verification_path": ["..."]
}
Rules:
- Treat explicit ADR/design files as more authoritative than raw transcript notes.
- Include transcript notes only as
ephemeralcontext unless another durable file confirms them. - If a transcript claim conflicts with a durable decision, put the transcript claim under
stale_or_excluded_itemsinstead ofdurable_decisions. - Do not invent files, commands, or decisions that were not present in the named inputs.
- Write only valid JSON to the requested output file.
- Write the JSON file to the requested path before you report anything. Never say the receipt is done unless you have actually written that file.
What ships with it
1 file 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.
- 1mo ago First seen · 36 lines · 20 tokens per session scan A 655b6e4edbfd
context-boundary-reporter is a skill published in the GitHub repository edonadei/caliper (221 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 306 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
bailian-memory
A personal memory service and setup guide for storing and retrieving a user's long-term preferences, background, and decisions. It explains when memory may be used and how users can enable, pause, resume, or control it.
doris-debug-resource-isolation
Use for Doris Workload Group / resource tag queue starvation, CPU/memory isolation leaks, and workload policy debugging. Commands: SHOW WORKLOAD GROUPS, EXPLAIN resource.
session-checkpoint
Re-orient a long, dense, or interruption-prone agent session without replacing the underlying evidence. Use when the user asks for a recap, orientation, simple teaching explanation, or spoken summary; when a session has accumulated many turns or tool calls; before context compaction; or when a Brief-Spec hook says a…
cf-learn
Extract educational notes for the human from the conversation (unlike /cf-remember, which stores project memory for AI recall). TRIGGER — substantial new technical knowledge, a debugging breakthrough, an architecture decision explained, or a complex explanation worth keeping; the user says "explain what we learned"…
cf-remember
Save project knowledge to docs/memory for AI recall (unlike /cf-learn, which writes educational notes for the human). TRIGGER — "remember this", "save this to memory", "document what we did", "capture this decision", "write this down", "note this", "record this convention"; after a non-obvious bug fix → bugs/, an…
cf-scan
Scan the project and populate memory (architecture, conventions, stack, features). Triggers: "scan the project", "scan the codebase", "bootstrap memory", "populate memory", "analyze the project". Token-heavy — always warn before proceeding.