project-context
Skill52 starsChanged 8 months agoMITView on GitHub
Initialize and maintain per-project runtime context (env, secrets, snapshots). Prefer invoking via research-workflow. TRIGGER when: new run needs env setup, preflight before experiment/eval, runtime fields missing (paths, API keys, GPU config, proxy), run snapshot needed, or shared-memory needs project config. DO NOT TRIGGER when: pure research (use deep-research), plan-only (use research-plan), or env already fully resolved.
33 other projects use a version of this.
Adopted by
Most recently taken up by
- advait/effect-durable-agenttheir own version, first seen Nov 8, 2026
- 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
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
- upex-galaxy/agentic-qa-boilerplate★ 26same name
- sergeeey/Claude-cod-top-2026★ 9same name
- perhapsspy/project-context★ 7same name
- advait/effect-durable-agent★ 4same 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 repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- deep-researchSkill
- experiment-executionSkill
- human-checkpointSkill
- memory-managerSkill
- paper-writingSkill
- research-planSkill
- research-workflowSkill
- run-governorSkill
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 6 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 24 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Distinctive: line 18
does not store heavy experiment artifacts (checkpoints, dataset caches, large logs)
- Distinctive: line 23
Use this skill when any of these are needed:
- Very specific: line 44
If multiple projects share one orchestration repo, isolate by project_slug.
- Distinctive: line 49
Do not ask for all fields at once.
- Very specific: line 54
if execution target is remote, consume reuse decision from run-governor first.
- Distinctive: line 55
ask only for missing required fields for the current task
- Very specific: line 58
when shared-memory retrieval/export is needed, ask the user where the local shared-memory repo should live if memory.shared_repo.path is …
- Distinctive: line 60
If new missing fields appear later, run preflight again and collect only deltas.
- Distinctive: line 67
never place secret content in stage reports or commit messages
“Common” is measured: kept by at least 6 in 10 of the 24 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
Project Context
Mission
Provide a reusable, private-by-default context layer for each project so environment information is collected once, reused across runs, and safely isolated from git history.
Scope boundary:
- manages runtime context and secrets only
- does not store heavy experiment artifacts (checkpoints, dataset caches, large logs)
- stores per-project shared-memory source configuration, but not shared-memory records
Trigger
Use this skill when any of these are needed:
- first-time project environment bootstrap
- preflight checks before experiment/report/eval execution
- missing runtime fields during task execution
- per-run context snapshot for reproducibility
- first use of shared-memory retrieval or export for a project
Private Directory Contract
Store all local runtime state under project root:
<project-root>/.project_local/<project_slug>/context.json<project-root>/.project_local/<project_slug>/secrets.json<project-root>/.project_local/<project_slug>/runs/<run_id>/runtime_snapshot.json
Rules:
.project_local/must be in.gitignore.context.jsonis non-sensitive.secrets.jsonis sensitive and must never be logged verbatim.- If multiple projects share one orchestration repo, isolate by
project_slug. - Initialize
.gitignoreif missing and append.project_local/if absent.
Incremental Collection Policy
Do not ask for all fields at once.
- infer task type (
report|sft|rl|eval|generic) - load existing
context.json+secrets.json - auto-detect non-sensitive environment values where possible
- if execution target is
remote, consume reuse decision fromrun-governorfirst; ask only if decision is missing - ask only for missing required fields for the current task
- during execution, allow blocker-only delta prompts (e.g. missing API URL/key)
- persist immediately for reuse
- when shared-memory retrieval/export is needed, ask the user where the local shared-memory repo should live if
memory.shared_repo.pathis missing
If new missing fields appear later, run preflight again and collect only deltas.
Security Policy
- set
<project-root>/.project_localand subdirectories to0700 - set
secrets.jsonto0600 - redact sensitive keys in all CLI output (
***) - never place secret content in stage reports or commit messages
Run Integration
Recommended order in research execution:
run-governorcollects and confirms mode +local|remotetargetrun-governorinitializesrun_idproject-contextpreflight resolves runtime context and consumes remote reuse decisionexperiment-executionruns with resolved contextproject-contextsnapshot writes run-scoped frozen context- shared-memory retrieval/export reuses
memory.shared_repo.*fromcontext.json
Script
Use helper script:
scripts/project_context.py
Examples:
python3 .agents/skills/project-context/scripts/project_context.py preflight \
--project-root . \
--project-slug my-sft-project \
--task-type sft \
--run-id 20260303_130000-my-sft-projectpython3 .agents/skills/project-context/scripts/project_context.py preflight \
--project-root . \
--project-slug my-sft-project \
--task-type generic \
--require memory.shared_repo.pathpython3 .agents/skills/project-context/scripts/project_context.py show \
--project-root . \
--project-slug my-sft-projectpython3 .agents/skills/project-context/scripts/project_context.py migrate-layout \
--project-root . \
--clean-emptyRequired Output for Operations
For each operation, emit:
Project: root and slugAction: preflight/show/snapshotState: loaded + newly collected fieldsPaths: local/context/secrets/snapshot/runtime/shared-memory pathsMissing: unresolved required fields (if any)
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.

