Durable, file-backed pipeline handoff BUS for the WHOLE squad (all worker agents + el-capitan). Persists per-run variables, per-phase outputs, and .ai_log/ evidence-PATH references to a PER-SESSION, git-ignored JSON file under .ai_log/ (.ai_log/session-<id>-<name>.json, one per run) that survives context compression; cleans stale .ai_log/ artifacts on init. On phase START, READ it to pull this phase's inputs (key fields + evidence paths); on phase COMPLETION, WRITE this phase's outputs (key result fields + .ai_log/ paths — never large inlined blobs). The standing pattern (R17): evidence -> .ai_log/; references + key fields -> pipeline-state; handoffs = state lookups, not inlined dumps. Coexists with the docs/ reports (R7/R8, the human record) + the .ai_log/ offload (R15). Originally built for the e2e-test-healer; now squad-wide. Use for ANY cross-phase handoff.
$npx -y skills add endorphin-ai/hasbrains-agent-kit --skill pipeline-stateInstalls into the current project.
Run `npx skills use "https://github.com/endorphin-ai/hasbrains-agent-kit" --skill "endorphin-ai/hasbrains-agent-kit/pipeline-state"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/endorphin-ai/hasbrains-agent-kit" that are relevant to the current task. Run `npx skills add "https://github.com/endorphin-ai/hasbrains-agent-kit"` and select the relevant skills, then follow their instructions.