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.
git clone --depth 1 https://github.com/bjcho4141/harness-bujangWrote 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/bjcho4141/harness-bujang/bujang-report)<a href="https://agentmods.dev/commands/bjcho4141/harness-bujang/bujang-report"><img src="https://agentmods.dev/badge/commands/bjcho4141/harness-bujang/bujang-report/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/bjcho4141/harness-bujang/bujang-report"><img src="https://agentmods.dev/badge/commands/bjcho4141/harness-bujang/bujang-report.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00026 | $0.00796 |
| Opus 5 | $0.00013 | $0.00398 |
| Sonnet 5 | $0.00005 | $0.00159 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
bujang-report scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/bujang-report
Read recent entries from harness_messages and produce a structured summary for the principal.
Action — execute now
Parse --days=N (default 1) and --detailed from the user's command arguments.
Step 1. Pull the data
Read from the local SQLite chat DB at .harness/chat.db:
sqlite3 .harness/chat.db <<SQL
SELECT id, created_at, from_role, to_role, type, severity, body
FROM harness_messages
WHERE created_at >= datetime('now', '-${N} day')
ORDER BY id ASC;
SQL
If .harness/chat.db doesn't exist, output: "No chat room exists yet for this project — open it once with /open-chat (or npx harness-bujang chat --create), then re-run /bujang-report."
Step 2. Aggregate
Compute:
- Total messages in window
- Type breakdown —
command/report/info/feedback - Severity breakdown —
info/warning/error - Per-role count — director, dev-team, code-review-team, etc.
Step 3. Group into work items
A "work item" is a chain of messages bounded by:
- Start — principal → director (command), or director → team (command) if no principal command was logged
- End — director → principal (report) at
severity=info(clean), OR last message if still open
For each work item:
- One-line subject (first command's first line, max 60 chars)
- Teams involved (distinct
from_rolevalues excludingdirectorandprincipal) - Final status: ✅ done (last msg is director → principal, severity=info), ⏳ in progress (no terminating director report), 🔴 blocked (latest message has severity=error or warning unresolved)
- Turnaround: first-message timestamp → last-message timestamp, formatted as
XmorXh Ym
Step 4. Open blockers
List messages with severity IN ('error', 'warning') that have no later message from the same to_role resolving them. Include the body (first 80 chars) and the source role.
Step 5. Output format
📊 Harness report — last <N> day(s)
Activity
Total messages: 47
Types: 8 commands · 35 reports · 4 info
Severity: 38 info · 6 warning · 3 error
Work items (3)
✅ Implement /api/health endpoint — 32m · dev-team, code-review-team, verifier-team
⏳ Migrate auth flow to OAuth — in progress · architect-team
🔴 Production incident: payment timeout — 14m, blocked on Inicis API key
Open blockers (1)
🔴 [security-team] Hardcoded API key in src/lib/payment.ts:42 — not yet patched
Top contributors
dev-team 14
director 9
code-review-team 8
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.
- 11d ago First seen · 87 lines · 26 tokens per session scan A 5df001f2e860
bujang-report is a command published in the GitHub repository bjcho4141/harness-bujang (7 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 796 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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.