Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add GhostlyGawd/engineering-board/plugin install 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-resume)<a href="https://agentmods.dev/commands/ghostlygawd/engineering-board/board-resume"><img src="https://agentmods.dev/badge/commands/ghostlygawd/engineering-board/board-resume.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 5.1 | $0.00021 | $0.00882 |
| Opus 5 | $0.00010 | $0.00441 |
| Sonnet 5 | $0.00004 | $0.00176 |
| Haiku 4.5 | $0.00002 | $0.00088 |
Grade A, and why
board-resume 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 6d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/board-resume: re-enable passive listening
Resume the engineering-board passive listener after a /board-pause. Restores the prior mode value (or null if there was none) and clears the paused_at timestamp. The next Stop-hook turn will resume invoking the finding-extractor.
What to do
Step 1: Resolve state file
State file: ${CLAUDE_PROJECT_DIR}/.engineering-board/session-mode.json
Step 2: Run the mode-transition guard
Delegate the refusal-matrix decision to the deterministic guard (single source of truth for ARCHITECTURE.md §11.5):
bash "$CLAUDE_PLUGIN_ROOT/hooks/scripts/board-mode-guard.sh" resumed
Inspect the exit code:
- 0 (ALLOW): parse the guard's stdout. It emits key=value lines including
RESTORE_MODE=<pm|worker|null>andRESTORE_DISCIPLINE=<tdd|review|validate|null>. Use these in Step 4 below. Then continue to Step 3. - 2 (NOOP): print the guard's stdout verbatim and stop. The canonical message for this branch is
Engineering board: not currently paused. No action taken.(Fires when no state file exists ORmodeis anything other than"paused".)
/board-resume has no REFUSE branch: every state either ALLOWs (paused) or NOOPs (not paused).
Step 3: Determine current session_id
Read ${CLAUDE_PROJECT_DIR}/.engineering-board/last-stop-stdin.json if it exists and extract the session_id field. If that file does not exist or has no session_id, use an empty string "".
Step 4: Rewrite the state file
Rewrite session-mode.json with content:
{
"mode": "<RESTORE_MODE from the guard's stdout; JSON null if null>",
"discipline": "<RESTORE_DISCIPLINE from the guard's stdout; only present when RESTORE_MODE == 'worker'; JSON null otherwise>",
"previous_mode": null,
"previous_discipline": null,
"paused_at": null,
"session_id": "<value from step 3>"
}
Field rules:
- If
RESTORE_MODE == null: write the literal JSONnull(not the string"null") formode, and JSONnullfordiscipline. - If
RESTORE_MODE == "pm": write"mode": "pm","discipline": null. - If
RESTORE_MODE == "worker": write"mode": "worker","discipline": "<RESTORE_DISCIPLINE>". The discipline MUST match the one captured at/board-pausetime so the (mode, discipline) round-trip is bit-exact per ARCHITECTURE.md §11.5. previous_modeandprevious_disciplinereset to JSONnull: the pause/resume cycle has completed.paused_atresets to JSONnull.session_idis a JSON string (possibly empty).
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.
- 6d ago First seen · 83 lines · 21 tokens per session scan A 0ffa4217a698
board-resume is a command published in the GitHub repository GhostlyGawd/engineering-board (0 stars, last pushed 7d ago), licensed MIT. It adds 21 tokens to every session and 882 once invoked, about $0.0001 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
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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.