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/kimsanguine/hplan/harness-excludegit clone --depth 1 https://github.com/kimsanguine/hplanWrote 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/kimsanguine/hplan/harness-exclude)<a href="https://agentmods.dev/commands/kimsanguine/hplan/harness-exclude"><img src="https://agentmods.dev/badge/commands/kimsanguine/hplan/harness-exclude.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 | $0.00058 | $0.00607 |
| Opus 5 | $0.00029 | $0.00303 |
| Sonnet 5 | $0.00012 | $0.00121 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
harness-exclude 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 5d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/harness-exclude
Instructions
You manage the hplan exclusions registry for: $ARGUMENTS
Decide sub-command
- If user is recording a Do-Not-Build →
add - If user is checking a new idea →
check - If listing →
list
add
python3 hplan/scripts/exclusions_registry.py add "<idea>" --why "<reason>" --reopen "<trigger>" --competitor "<name>" [--competitor "<name>"]. Require --reopen to be an action-shaped condition (e.g., "enterprise compliance interviews 3+"), not vague.
check
python3 hplan/scripts/exclusions_registry.py check "<idea>". Threshold 0.40 by default. If COLLISION, confirm reopen_trigger met before proceeding with other gates.
list
python3 hplan/scripts/exclusions_registry.py list — dump JSONL.
Profile Isolation (per-client / per-project)
Use --profile <name> to maintain separate exclusion registries for different clients or projects:
# Add an exclusion for a specific client
python3 hplan/scripts/exclusions_registry.py add "AI marketing copy generator" \
--why "Established incumbents cover this" \
--reopen "3+ enterprise compliance customers request it" \
--profile client-acme
# Check only client-acme's registry
python3 hplan/scripts/exclusions_registry.py check "AI marketing copy" --profile client-acme
# List all entries for a profile
python3 hplan/scripts/exclusions_registry.py list --profile client-acme
# Global registry (no --profile = default behavior)
python3 hplan/scripts/exclusions_registry.py check "AI marketing copy"
When --profile is omitted, the global registry at harness/exclusions.jsonl is used. Profile registries are stored at harness/profiles/<profile>/exclusions.jsonl. Add harness/profiles/ to .gitignore to prevent client data from being committed.
Output Format
For add:
- id —
ex-YYYY-MM-DD-XXXXX - exclusion text, why, reopen_trigger, competitors
For check:
- verdict — COLLISION or CLEAR
- matches — array of prior exclusions with overlap score
- guidance — next action
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.
- 5d ago First seen · 63 lines · 58 tokens per session scan A 6f45caa15990
harness-exclude is a command published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 19d ago), licensed MIT. It adds 58 tokens to every session and 607 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
openehr-explain
One-stop router that explains or looks up any openEHR thing — auto-detects an archetype, a template, an RM/AM/BASE type, an RM structural concept, an ADL idiom, an AQL query or keyword, or a terminology code (replaces /archetype-explain, /template-explain, /type-spec, /rm-structure, /adl-idiom, /terminology).
co-change
List files that historically co-change with a target (git log heuristic; COCHANGE-style).
harness
Run the full Auto-Harness orchestration flow. /auto-harness:harness.
start-design-plan
Start collaborative design process with brainstorming and planning.
start-implementation-plan
Create implementation plan from design document.
checklist
Generate a custom checklist for the current feature based on user requirements.