chronicle
Skill0 starsChanged 2 months agoMITView on GitHub
Preserve operational history and intent across agent sessions. Use when resuming work, recording a decision, preparing a destructive or bulk operation, verifying a deployment, correcting a claim, reconstructing a captured file version, or handing off unfinished work.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- shizhigu/chronicletheir own version, first seen Oct 20, 2026
- microsoft/vscodetheir own version, first seen Oct 13, 2026
- Alexander-Tyagunov/magiciantheir own version, first seen Sep 28, 2026
- karloows/orchrafttheir own version, first seen Sep 22, 2026
- leaf76/agent-skillstheir own version, first seen Aug 17, 2026
- Galliard7/skillstheir own version, first seen Jun 27, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- microsoft/vscode★ 195ksame name
- Alexander-Tyagunov/magician★ 14same name
- 3zequiel3/chronicle★ 4same name
- shizhigu/chronicle★ 2same name
- Galliard7/skills★ 1same name
- karloows/orchraft★ 1same name
- madebygps/skills★ 1same name
- leaf76/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.
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 4 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Run chron resume in the project root.
- Very specific: line 21
If the CLI is missing, install with pipx install 'git+https://github.com/AntreasAntoniou/chronicle.git'.
- Distinctive: line 35
Before a destructive or bulk operation:
- Very specific: line 49
After publication or deployment, record observed state using chron landed --ext and --verified.
- Very specific: line 64
Only captured versions can be recovered.
- Distinctive: line 73
Keep secrets out of narrative entries and keep the ledger, CAS, transcripts, and canvas private.
- Distinctive: line 75
Keep operational history here.
- Distinctive: line 78
Read references/codex.md before experimenting with Codex hooks.
“Common” is measured: kept by at least 6 in 10 of the 8 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
Chronicle
Chronicle separates observed events from the intent only the person or agent doing the work can state. Capture requires installed, active hooks; check coverage before assuming the trace is complete.
Resume first
Run chron resume in the project root. Read unresolved questions and state declarations.
Then record what you are taking up:
chron open "continue search" --state "empty results are intentional staging"If the CLI is missing, install with
pipx install 'git+https://github.com/AntreasAntoniou/chronicle.git'. Installing the skill
does not install hooks or establish capture coverage.
Five moments worth recording
| Command | What to record |
chron open | Your belief about current state and what you are taking up |
chron arm | The operation, intent, reversibility class, and verified restore path |
chron decision | The choice, reason, and any ambiguous state that is intentional |
chron landed | A verified external change with resource/version and rollback references |
chron close | Where work stopped, what remains undone, and open questions |
Before a destructive or bulk operation:
chron arm "replace the staging index" \
--intent "load the verified replacement" \
--class R1 \
--restore "snapshot path and tested restoration command" \
--verified "restoration tested on a disposable copy"R0 is fully reversible, R1 needs a recovery artifact, and R2 is irreversible. An ARM does not grant user authority or prove that a host gate is active. Follow the user's scope and verify hook integration separately.
After publication or deployment, record observed state using chron landed --ext and
--verified. A successful command alone does not prove an external change.
Correct and recover
Append chron correct with the original entry ID, truth, and evidence. Preserve history.
chron history src/app.py
chron show src/app.py --at 2h
chron restore src/app.py --at 2h --to /tmp/recovered-app.py
chron search "search index"
chron doctorOnly captured versions can be recovered. State gaps explicitly. Use chron experiment
and chron abandoned for attempts and dead ends, quoting measured results only.
Inference and privacy
- Narrated entries marked
inferredare hypotheses. Inspect anchored events before acting; append a firsthand statement when you can resolve an uncertainty. - Narration requires an explicit model, can incur cost, and sends trace content to that provider. Review its dry-run prompt first.
- Keep secrets out of narrative entries and keep the ledger, CAS, transcripts, and canvas private. Redaction does not guarantee detection of every embedded secret.
- Keep operational history here; route commitments to a task tracker and lasting knowledge to canonical project documentation.
Read references/codex.md before experimenting with Codex hooks. Configuration, trust, execution, and verified coverage are separate states.
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.

