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 adamwstauffer/shidler --skill breakpointgit clone --depth 1 https://github.com/adamwstauffer/shidlerWrote 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/adamwstauffer/shidler/breakpoint)<a href="https://agentmods.dev/skills/adamwstauffer/shidler/breakpoint"><img src="https://agentmods.dev/badge/skills/adamwstauffer/shidler/breakpoint/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/adamwstauffer/shidler/breakpoint"><img src="https://agentmods.dev/badge/skills/adamwstauffer/shidler/breakpoint.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 | $0.00135 | $0.02175 |
| Opus 5 | $0.00068 | $0.01087 |
| Sonnet 5 | $0.00027 | $0.00435 |
| Haiku 4.5 | $0.00014 | $0.00217 |
Grade A, and why
breakpoint 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 8d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/breakpoint — Session pickup prompt
A breakpoint captures everything a fresh session needs to resume without re-reading the whole transcript, in one structured block. The output is the deliverable: it goes into the conversation and is persisted to a dated file so it survives /compact or seeds the next session even if the conversation context is lost entirely.
Direction is forward and lateral: what's done, what's in flight, what's blocked, where to pick up.
This repo is course materials, not shipping software — so "work in flight" means an active grading pass, a docs/decisions/ memo mid-draft, or a course restructure, not a CI pipeline. The inputs below are retargeted accordingly.
When to break
Strong signals to checkpoint (the skill should fire on any of these):
- The user says "pickup prompt", "breakpoint", "hand off", "checkpoint", or is about to
/compact//clear. - A grading pass is mid-flight —
STAGE{N}_GRADES.mdpartially written, some students scored and some not. - End of a phase — a course restructure or a multi-file
git mvjust landed, before starting the next. - Before a risky operation — a
git mvrestructure ofcourses/, an archive move, a force-push, a worktree teardown. - Context is getting long and a compaction is likely.
When in doubt, ask; don't force it.
Inputs (gather in this order; skip a line silently if the command errors or returns nothing)
- Current branch + worktree state.
git branch --show-current,git status --short,git worktree list. Note which branch each worktree holds. Count worktrees and flag concurrent-session hazards — more than a couple usually means another session shares the repo; a worktree nested inside.claude/is the nested-creation gotcha. - Uncommitted / unpushed work — scope to THIS session's branch, not all local branches.
- Dirty tree:
git status --short. - Unpushed commits on the current branch:
git rev-list --count @{u}..HEAD(orgit log @{u}..HEAD --oneline); if there's no upstream, the branch itself is unpushed. - Do NOT use
git log --branches --not --remotes— it sweeps every local branch (including other sessions' work) and produces a misleading pile of "unpushed commits" that isn't yours. - Unpushed work is the highest-loss-risk state — surface it first, but only the work that's actually yours.
- Untracked stray files (
git status --short??lines) — this repo routinely has untracked.claude/worktrees/and draft memos; note which are intentional scratch vs. work that needs committing, so the next session doesn't blind-git add.
- Dirty tree:
- Open PRs + their state. If
ghis available:gh pr list --state open --author "@me" --json number,title,headRefName,baseRefName,isDraftand, for each relevant PR,gh pr checks <n>. Capture stack relationships (base → head) explicitly. - Recently merged PRs (last ~24h or this session):
gh pr list --state merged --limit 10 --json number,title,mergedAt— so the next session doesn't re-do landed work. - Task list state. Read the current task list (in-progress / pending / completed). If empty but work is clearly mid-flight, reconstruct from the transcript.
- In-flight decision memos + plans.
Glob docs/decisions/*.md(most recent first); flag any withstatus: proposedthat this session is executing or that await ratification. Quote the memo's open question, don't paraphrase. - Active grading passes. If a grading task is live: which offering, which stage, which
STAGE{N}_GRADES.md, how many students scored vs. remaining, whether the post-deadline sweep has run (feedback_regrade_policy— a stage locks once its sweep runs). Never copy score numbers into the pickup block (feedback_score_privacy— scores live only in the internal grades file and instructor email). - Standing constraints. Grading/house rules governing the current work (relevant
feedback_*memories, a locked decision memo). Quote the constraint.
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.
- 8d ago First seen · 111 lines · 135 tokens per session scan A 549615aadf5d
breakpoint is a skill published in the GitHub repository adamwstauffer/shidler (10 stars, last pushed yesterday), licensed MIT. It adds 135 tokens to every session and 2,175 once invoked, about $0.0007 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
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…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.