Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/backchainai/backchain-plugins/workingnpx skills add backchainai/backchain-plugins --skill workinggit clone --depth 1 https://github.com/backchainai/backchain-pluginsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00097 | $0.01183 |
| Opus 5 | $0.00048 | $0.00592 |
| Sonnet 5 | $0.00019 | $0.00237 |
| Haiku 4.5 | $0.00010 | $0.00118 |
Grade A, and why
working scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working Memory
Manage ephemeral .memory/ directories for persisting structured conversation state across multi-day Claude Code sessions. Three commands cover the full lifecycle:
| Command | Purpose |
|---|---|
/engram:working checkpoint |
Create or update .memory/ with current conversation state |
/engram:working promote |
Move .memory/ artifacts to permanent knowledge locations |
/engram:working cleanup |
Delete promoted content, preserve the directory |
The skill is invoked as /engram:working (the plugin-qualified skill name) followed by the subcommand. Natural-language phrasings like "checkpoint working memory" trigger the same dispatch.
Working memory vs auto memory
This skill complements Claude Code's native auto memory. They serve different purposes:
| Working memory (this skill) | Auto memory (native) | |
|---|---|---|
| Trigger | User-initiated (/engram:working checkpoint) |
Automatic (Claude decides what's worth remembering) |
| Content | Structured work state — todos, decisions, questions | Implicit learnings — corrections, preferences, patterns |
| Lifecycle | Ephemeral: checkpoint → promote → cleanup | Persistent until manually deleted |
| Scope | Per-directory (.memory/ in CWD) |
Per-project (~/.claude/projects/<project>/) |
| Promotion path | Explicit: ADRs, issue-tracker entries, docs | Implicit: stays in MEMORY.md / topic files |
Use working memory for structured in-flight work that warrants a deliberate promotion gate. Let auto memory handle preferences, build insights, and behavioral corrections that Claude discovers organically.
During checkpoint, do not capture items that auto memory already handles — user preferences, build commands, debugging shortcuts, code style. Focus on actionable work state.
During promote, decisions too small for a full ADR but worth persisting can be written into auto memory using its standard frontmatter format. Once written there, they are auto memory's responsibility; working does not re-modify them.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 93 lines · 97 tokens per session scan A b2c6b1dfc121
working is a skill published in the GitHub repository backchainai/backchain-plugins (4 stars, last pushed 27d ago), licensed Apache-2.0. It adds 97 tokens to every session and 1,183 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
kayba-stage-3-metrics
Define metrics from Kayba insights, implement them as Python measurement code, run against traces, and iterate until the metrics are clean and meaningful. Trigger when the user says "run stage 3", "define metrics", "build metrics", "compute baselines", or when invoked by the kayba-pipeline orchestrator. Requires…
kayba-stage-5-action-plan
Triage each insight into discard/code-fix/prompt-fix and produce a prioritized action plan with specific recommendations. Trigger when the user says "run stage 5", "make action plan", "triage skills", or when invoked by the kayba-pipeline orchestrator. Requires eval outputs from stages 1-4.
kayba-stage-6-hitl
Human-In-The-Loop gate that presents the action plan with full context, collects an informed approval/modification/rejection decision, and records the outcome. Trigger when the user says "run stage 6", "HITL review", "approve action plan", or when invoked by the kayba-pipeline orchestrator. Requires eval/actionplan.md…
kayba-stage-2-domain-context
Gather domain context about the repository and agent — system prompt, tool definitions, domain docs, and behavior patterns from traces. Trigger when the user says "run stage 2", "gather context", "domain context", or when invoked by the kayba-pipeline orchestrator.
kayba-stage-7-fixer
Implement the approved fixes from the action plan and log all changes. Trigger when the user says "run stage 7", "implement fixes", "apply action plan", or when invoked by the kayba-pipeline orchestrator. Requires eval/actionplan.md to exist.
kayba-pipeline
End-to-end agent evaluation and improvement pipeline. Takes a traces folder and optional HITL flag, then orchestrates sub-agents through 7 stages — each stage is its own skill invoked by a dedicated sub-agent. Trigger when the user says "run the pipeline", "kayba pipeline", "evaluate and fix", "full eval", "analyze…