checkpoint
Skill1 starsChanged 3 months agoMITView on GitHub
Record what a future session must know into this project's memory files. Use when work reaches a durable outcome such as a fix, a discovered constraint or a paused task, or when the user asks to save state.
91 other projects use a version of this.
Adopted by
Most recently taken up by
- TheLunchTrae/claude-code-configstheir own version, first seen Nov 8, 2026
- codewithmukesh/dotnet-claude-kittheir own version, first seen Nov 8, 2026
- pedrohcgs/claude-code-my-workflowtheir own version, first seen Nov 7, 2026
- flonat/flonat-researchtheir own version, first seen Nov 3, 2026
- jboczek/skillstheir own version, first seen Nov 1, 2026
- AhmedMerza/claude-skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use aside, spinoff and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
TheKREATORSSkillaside
Answer a quick side question without interrupting or losing context from the current task. Resume work automatically after answering.
Also in 3 projects that use this
AhmedMerzaSkillspinoff
After a branch is finished, harvest the work it made CHEAP — the helper you wrote that four other sites now hand-roll, the plumbing that turned a deferred feature small, the pattern that just split the codebase in two. Produces a follow-up backlog (0–3 candidates, feeding /issue), NEVER commits on the current branch. Invoke with /spinoff at the tail of the chain — after /fix-review has settled the review findings, before the MR merges — or when the user asks \"what else should we do while we're here / what did this unlock / anything to follow up on\". This is ship-check's optional twin — that finds what's MISSING and blocks the merge; this finds what's now CHEAP and blocks nothing. Restraint-gated: \"nothing spun off\" is the common and correct answer, and a finding that would have been equally valid before this branch is not a finding.
Also in 3 projects that use this
- TheKREATORSSkill
instinct-export
Export instincts from project/global scope to a file
Also in 3 projects that use this
seek888Skillopen-gstack-browser
Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed and chat. Anti-bot stealth built in. Use when asked to "open gstack browser", "launch browser", "connect chrome", "open chrome", "real browser", "launch chrome", "side panel", or "control my browser". Voice triggers (speech-to-text aliases): "show me the browser".
Also in 5 projects that use this
diego-tobalinaSkillbuild-fix
Fix build and compilation errors systematically. Run when build fails.
Also in 5 projects that use this
- seek888Skill
design-html
Design finalization: generates production-quality Pretext-native HTML/CSS. Works with approved mockups from /design-shotgun, CEO plans from /plan-ceo-review, design review context from /plan-design-review, or from scratch with a user description. Text actually reflows, heights are computed, layouts are dynamic. 30KB overhead, zero deps. Smart API routing: picks the right Pretext patterns for each design type. Use when: "finalize this design", "turn this into HTML", "build me a page", "implement this design", or after any planning skill. Proactively suggest when user has approved a design or has a plan ready. (gstack) Voice triggers (speech-to-text aliases): "build the design", "code the mockup", "make it real".
Also in 5 projects that use this
- +2 more from TheKREATORS
- +2 more from seek888
Other versions91 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 91
- pedrohcgs/claude-code-my-workflow★ 1.7ksame name
- codewithmukesh/dotnet-claude-kit★ 808same name
- leonvanzyl/agentic-coding-starter-kit★ 447same name
- myICOR/myPKA★ 319same name
- hsantanna88/clo-author★ 262same name
- hugosantanna/clo-author★ 262same name
- sterlingcrispin/claude_slash_commands★ 200same name
- flonat/flonat-research★ 150same name
- josipjelic/orchestrated-project-template★ 96same name
- panayiotism/claude-harness★ 79same name
81 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repositoryOne other file it gives its agents.
- memory-initSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 85 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 45
Get the real date: Read the system date before writing it anywhere.
- Distinctive: line 51
Route and write: Place each survivor per the table, one or two sentences each.
“Common” is measured: kept by at least 6 in 10 of the 85 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
A checkpoint is small. It captures what would otherwise have to be rediscovered, and nothing else.
Needs memory/. Run memory-init if it is missing.
What earns a line
One test, applied to every candidate: would a future session waste time, or repeat a mistake, without this?
Earns a line:
- A constraint found the hard way, and what it costs to break it.
- A fix, recorded by its cause rather than its symptom.
- Something that turned out to be deliberate and must not be "fixed".
- Where work stopped, and the one concrete next action.
Fails the test:
- Anything the code, the tests or the commit history already state.
- Narration of what was tried.
- Detail that only matters inside this conversation.
A candidate that fails is dropped, not shortened.
Routing
| The thing | Goes to | How |
| Changes what the project is, or how to run it | PROJECT.md | Edit in place, and delete the line it replaces |
| What happened this session | SESSIONS.md | Append at top |
| A settled choice with a rejected alternative | DECISIONS.md | Not yours to write. Say so, and tell the user to record it themselves |
Locking a decision is the user's act, not yours. Recording that one was made is fine; writing it into DECISIONS.md on your own initiative is not.
PROJECT.md earns its keep by staying short. Replacing a stale line there is the point, not a side effect.
Deleting memory is approval-gated, and this skill does not route around that gate. A removal you can pair with the line that replaced it is a replacement, and it is yours to make. Everything else stays where it is and goes into your report for the user to decide on.
Steps
- Get the real date. Read the system date before writing it anywhere. A conversation can stay open past midnight. Done when today's date came from the system rather than from memory.
- List the candidates. Everything from this session that might earn a line, written out. Done when every item on the list has visibly passed or failed the test above.
- Route and write. Place each survivor per the table, one or two sentences each. Done when every survivor sits in exactly one file.
- Replace, do not sweep. Delete only a line that the content you just wrote directly replaces: same subject, now superseded by something specific you added in this pass. Anything else that looks stale, duplicated or wrong stays where it is and goes into your report instead, for the user to approve. Done when every deletion you made can be paired with the exact line that replaced it, and everything else you noticed is in the report rather than removed.
- Report. Name the files changed, quote the lines added, pair each deletion with its replacement, and list what you left untouched for review. Done when the user can see exactly what was recorded and exactly what was removed without opening a file.
Entry shape
SESSIONS.md, newest at top:
## 2026-07-30
Done: what is now true, and how it was verified
Open: what is unfinished
Next: the one concrete next actionDone without the verification is a claim, not a record. Where something was not verified, say that instead.
A note on what this pack does not include
This is the free two-skill pack. Two jobs are left to you here: locking a
decision into DECISIONS.md, and clearing out stale lines. Both are deliberate
acts that this skill will not perform on its own initiative.
The full stack adds skills that handle both with your approval, plus cold-boot and compaction safety. Details at https://getclearstack.carrd.co
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.