agentleFS
yogsoth-aiyogsoth-ai/context-management/skills/context-checkpoint/SKILL.md

context-checkpoint

Skill2 starsChanged 5 months agoApache-2.0View on GitHub

Append research process and results to the current Phase's context file. Each append MUST contain >=500 lines of markdown covering both process and results. Use this skill at plan-designated checkpoint points — typically after each strategy completes or at key decision nodes within a research Phase.

5 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions5 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 5

    1. adamentwistle/fable-skills★ 98same name
    2. clarity-digital-development/tworkflow★ 47same name
    3. cyrus-tt/claude-context-checkpoint★ 9same name
    4. pauloribeiro16/my-skills★ 1same name
    5. prasadmogulothu/agent-skills★ 0same name

    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.

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Content scope: Must record both PROCESS (what was done, searched, considered) and RESULTS (what was found, decided, what remains open).

    line 22
  2. Very specific:

    Import context-init. This is idempotent — if the context file for the current Phase already exists, it skips creation and returns the …

    line 29
  3. Distinctive:

    Update the row for the current context file:

    line 80
  4. Very specific:

    Update the Last Updated timestamp (call scripts/timestamp.py for current time)

    line 82

“Common” is measured: kept by at least 6 in 10 of the 4 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Context Checkpoint

Append research process and results to the current Phase's context file.

When Called

Multiple times within a Phase, at plan-designated checkpoint points:

step: "import context-management:context-checkpoint"

Typically triggered after each strategy completes or at key decision nodes.

Hard Constraints

  1. Minimum content volume: Each checkpoint append MUST contain >=500 lines of substantive markdown. This is non-negotiable. The 500 lines mean real content; inflating the count by hard-wrapping prose, padding, or repetition is gaming the constraint and is explicitly disallowed. The purpose is genuine information density for future reference.
  2. Content scope: Must record both PROCESS (what was done, searched, considered) and RESULTS (what was found, decided, what remains open).
  3. No mid-paragraph line breaks: Write each prose paragraph as a single continuous line. Do not insert newlines inside a paragraph to wrap it at a column width. Newlines are only for separating paragraphs, list items, headings, and fenced code blocks. (A paragraph being one long line does NOT count toward the 500-line minimum being met — write more substance, never more wrapping.)

Execution Protocol

Step 1: Ensure Context File Exists

Import context-init. This is idempotent — if the context file for the current Phase already exists, it skips creation and returns the existing file path.

Step 2: Locate Current Context File

Determine the current Phase's context file path by:

  • Using the path returned by context-init, OR
  • Checking context/INDEX.md for the most recent entry matching the current Phase

Step 3: Append Checkpoint Content

Append a new section to the context file:


---

## Checkpoint: <Descriptive Name>

<CC writes >=500 lines here covering process + results>

Content format: CC has full autonomy. A default semi-structured template is available as guidance but not mandatory:


---

## Checkpoint: <Descriptive Name>

### Objective
What this stage aimed to accomplish.

### Process Summary
What was done — searches performed, papers read, methods applied, decisions made along the way.

### Key Findings
The substantive results — discoveries, patterns, important papers, technical details.

### Decisions Made
Choices made during this stage and their rationale.

### Open Questions
What remains unresolved, what needs further investigation.

CC may use this template, modify it, combine sections, add new sections, or write in completely free-form style. The only requirements are:

  • =500 lines of markdown

  • Coverage of both process and results

Step 4: Update INDEX.md

Update the row for the current context file:

  • Increment the Checkpoints count
  • Update the Last Updated timestamp (call scripts/timestamp.py for current time)

Content Guidance

The checkpoint is a detailed record for future reference. Write as if the reader has zero context about what happened during this research stage. Include:

  • Specific searches performed (queries, databases, filters)
  • Papers found and their relevance
  • Methods applied and their outcomes
  • Decisions made and their rationale
  • Surprises, dead ends, pivots
  • Quantitative results where applicable
  • Open threads for future investigation

The 500-line minimum exists because sparse checkpoints are useless for recovery. Write generously — this is a research log, not a summary.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.