project-context
Skill4 starsChanged 6 days agoMITView on GitHub
State effect-durable-agent's operating context (who consumes it, what is one-way, what failure costs most), the risk proportion every principle applies in, and the mise tasks. Read before making poteto-mode decisions in this repository.
- Installs packages
33 other projects use a version of this.
Adopted by
Most recently taken up by
- shinpr/ai-coding-project-boilerplatetheir own version, first seen Nov 8, 2026
- upex-galaxy/agentic-qa-boilerplatetheir own version, first seen Nov 7, 2026
- egorfedorov/claude-context-optimizertheir own version, first seen Nov 1, 2026
- ritamgh/claude-skillstheir own version, first seen Nov 1, 2026
- OpenxIntelligence/Coding-Agent-Skillstheir own version, first seen Nov 1, 2026
- I-Onlabs/claude-code-skillstheir own version, first seen Oct 25, 2026
Used with
Projects with it also use code-review.
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.
GoogleSkillcode-review
Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.
Also in 3 projects that use this
Other versions33 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 33
- shinpr/ai-coding-project-boilerplate★ 236same name
- egorfedorov/claude-context-optimizer★ 127same name
- TenureAI/PhD-Zero★ 52same name
- upex-galaxy/agentic-qa-boilerplate★ 26same name
- sergeeey/Claude-cod-top-2026★ 9same name
- perhapsspy/project-context★ 7same name
- aida-core/aida-marketplace★ 4same name
- I-Onlabs/claude-code-skills★ 4same name
- IgorBabikov/Flowcairn★ 4same name
- OpenxIntelligence/Coding-Agent-Skills★ 4same name
23 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 repository3 other files it gives its agents.
- coding-standardsSkill
- releaseSkill
- verifySkill
The file
Files
Project context
Status: implemented
Who uses it
effect-durable-agent (EDA) is published publicly as three lockstep npm packages,
effect-durable-agent, effect-durable-agent-cloudflare and effect-durable-agent-celld
(releasing), but GoGuardian's Gia (goguardian/gia) is its only
consumer. Gia pins an exact published version through its pnpm catalog and runs EDA sessions in
production Durable Objects. It carries this repository as a submodule but installs EDA from npm,
so a change reaches Gia only through a release and a pin bump. With one consumer, favour moving
fast over compatibility ceremony: a breaking API change is fine when Gia's pin-bump PR absorbs it.
What is one-way
- Published versions. npm versions are immutable; never reuse one (releasing).
- Stored histories. Event logs, reducer and sink checkpoints and transcript tables live in deployed Durable Objects and must stay readable by every later version. Compatibility is forward-only: rolling a host back to an older version after a newer one has written is not supported, so a bad release is fixed forward.
- Schema migrations.
_eda_schema_migrationsmigrations are forward-only (spec). - Wire contracts. The WebSocket protocol (websocket-protocol),
the RPC surface and every exported subpath in the three
package.jsonexportsmaps (CONTRIBUTING).
What failure costs most
A release that misreads, rewrites or fails to replay a stored history in Gia's production Durable
Objects: users lose sessions, and the bytes are already published. Every change states in
CHANGELOG.md what it does to storage, protocol and API compatibility ("No storage, protocol or
API change" when nothing). Treat any change to durable event schemas, reducers, replay or
migrations as the high-risk class.
Task runner
mise, from the repository root (mise.toml); tasks wrap the package.json scripts.
| Task | Does |
mise run install | pnpm install plus the Effect tsgo oxlint patch. Run first in a new checkout. |
mise run check | Format, lint and typecheck every package and the examples. |
mise run test | Unit, property, example and real workerd/celld host-conformance suites. |
mise run ci | What CI runs: build, check, test, replay-memory, lockstep versions, package check. |
mise run package:check | Packs each package and installs it into an isolated Worker. |
mise run lint:fix | Automated format and lint fixes. |
Follow-ups
List them in the reply. GitHub issues on advait/effect-durable-agent are for users' reports.
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.