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 commands/ghostlygawd/engineering-board/board-remembergit clone --depth 1 https://github.com/GhostlyGawd/engineering-boardWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/ghostlygawd/engineering-board/board-remember)<a href="https://agentmods.dev/commands/ghostlygawd/engineering-board/board-remember"><img src="https://agentmods.dev/badge/commands/ghostlygawd/engineering-board/board-remember.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00059 | $0.00645 |
| Opus 5 | $0.00030 | $0.00322 |
| Sonnet 5 | $0.00012 | $0.00129 |
| Haiku 4.5 | $0.00006 | $0.00064 |
Grade A, and why
board-remember 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 2d ago.
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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/board-remember: explicit learning capture
Write one durable learning to the board right now, without waiting for the
learnings curator's recurrence threshold. The learning file matches the
curator's shape (so board-index-check.sh and the validator stay green) and
carries source: remember so curator-promoted and user-remembered learnings
stay distinguishable.
What to do
Step 1: Parse arguments
Split $ARGUMENTS on the first -- separator (space-dash-dash-space):
- Everything before it is
<insight>: the durable lesson to remember. - Everything after it (optional) is
<context>: when/where the insight applies.
If $ARGUMENTS is empty or whitespace-only, print:
Usage: /board-remember <insight> [-- <context>]. No action taken.
Then stop.
Step 2: Run the remember script
Run:
bash $CLAUDE_PLUGIN_ROOT/hooks/scripts/board-remember.sh "<insight>" "<context>"
(Omit the second argument when no context was given.) The script resolves the
board via hooks/scripts/board-paths.sh (router order:
engineering-board/BOARD-ROUTER.md to docs/boards/BOARD-ROUTER.md to legacy
docs/board/) and targets the first listed project's board. To target a
different board, pass --board-dir <board-dir> as the first argument.
Step 3: Report the result
Handle exit codes:
-
Exit 0: the script printed a JSON object. Report the
id,title, andfilefields plainly, e.g.:Remembered as L006: Always flush the buffer before close (learnings/L006-always-flush-the-buffer-before-close.md). -
Exit 2 (no board): print
No board found — run /board-init first.and stop. -
Exit 1 (usage): print the usage line from Step 1 and stop.
Notes
- The MCP twin is the
board_remembertool (project,insight,context?): identical file output. use whichever surface you have. - Learnings written this way have
recurrence: 1andconfidence: medium. the curator may later raise confidence when the same pattern recurs across resolved entries. - The insight's first line becomes the entry title (newlines are flattened).
the full insight becomes
## Takeawayand the context becomes## When this applies.
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.
- 2d ago First seen · 72 lines · 0 tokens per session scan A fa641f037e95
board-remember is a command published in the GitHub repository GhostlyGawd/engineering-board (0 stars, last pushed 3d ago), licensed MIT. It adds 59 tokens to every session and 645 once invoked, about $0.0003 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.