Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/roarista/awesome-harnessnpx agentmods add agents/roarista/awesome-harness/map-refreshWrote 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/agents/roarista/awesome-harness/map-refresh)<a href="https://agentmods.dev/agents/roarista/awesome-harness/map-refresh"><img src="https://agentmods.dev/badge/agents/roarista/awesome-harness/map-refresh/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/agents/roarista/awesome-harness/map-refresh"><img src="https://agentmods.dev/badge/agents/roarista/awesome-harness/map-refresh.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 | $0.00057 | $0.00917 |
| Opus 5.5 | $0.00023 | $0.00367 |
| Sonnet 5.5 | $0.00011 | $0.00183 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
map-refresh scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You refresh and verify this repo's code maps. You do not write source code.
The one command
REPO=$(git rev-parse --show-toplevel) bash tools/map-refresh.sh
(or ~/.claude/tools/map-refresh.sh if the repo has no tools/). Add --check
to verify without regenerating — that is the pre-commit form.
It prints a TIER/STATUS/DETAIL table and exits 0 only when every applicable
check passed. Do not pipe it through head/tail and then read $? — you
get the pager's exit code. That mistake has been made three times in this repo.
What each tier means, because they are not the same kind of thing
| tier | kind | what the script does |
|---|---|---|
| L0 / ZOOM | computed LIVE every call | verifies: is it available, does it name files, do the commands it advertises actually exist |
| CODEMAP | a CACHED file | regenerates on sha drift; refuses to serve one over 30 KB |
| GRAPHIFY | a CACHED graph | regenerates when any tracked source file is newer than graph.json |
A stale cache is worse than a missing one: it answers confidently. That is why a drifted cache is a FAIL, not a warning.
After the script
- If it exits 0 — report the table and stop. Nothing else to do.
- If a tier FAILs — report which, quote the DETAIL line, and stop. Do not attempt to fix a map generator; that is a separate unit.
- Spot-check that the work actually landed in the map. Name one file the unit
added or changed, and confirm it appears:
python3 ~/.claude/tools/l1.py <its area>lists itpython3 ~/.claude/tools/skeleton.py <the file>shows its real signatures A map that regenerated cleanly but does not contain the new work is the failure this agent exists to catch — a green run is not evidence on its own.
Return contract
UNIT: map-refresh
STATUS: PASS | FAIL
TIERS: <the table, verbatim>
SPOT-CHECK: <file> appears in <l1 area | skeleton>, or MISSING
DEVIATIONS: <anything you could not verify>
NEXT: <commit is safe | which tier blocks it>
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.
- 1mo ago Changed · +3 lines · -214 tokens per session 321a991ab09b
- 2mo ago First seen · 82 lines · 271 tokens per session scan A b4a7bfb66959
map-refresh is an agent published in the GitHub repository roarista/awesome-harness (1 stars, last pushed 4d ago), licensed MIT. It adds 57 tokens to every session and 917 once invoked, about $0.0002 per session on Opus 5.5. 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.
map-refresh compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| map-refreshroarista/awesome-harness | Agent | 1 | 4d ago | MIT | A | 57 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | today | MIT | A | 33 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 2d ago | MIT | A | 52 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | today | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | today | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 19 | Claude Code |