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/Khar-AG/t-800-agentnpx agentmods add commands/khar-ag/t-800-agent/t800-fixWrote 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/khar-ag/t-800-agent/t800-fix)<a href="https://agentmods.dev/commands/khar-ag/t-800-agent/t800-fix"><img src="https://agentmods.dev/badge/commands/khar-ag/t-800-agent/t800-fix/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/khar-ag/t-800-agent/t800-fix"><img src="https://agentmods.dev/badge/commands/khar-ag/t-800-agent/t800-fix.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 | $0.00000 | $0.01075 |
| Opus 5.5 | $0.00000 | $0.00430 |
| Sonnet 5.5 | $0.00000 | $0.00215 |
| Haiku 4.5 | $0.00000 | $0.00108 |
Grade A, and why
t800-fix 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/t800-fix — правка по fix-pack (PATCH)
Зачем: узкая правка существующих agents / skills / commands / rules / hooks по pack — без полного DEEP /t800-start.
Контракт: shared/fix-pipeline-contract.md.
Loop / STATE / gates: shared/loop-engineering-contract.md.
Закон
Не делай полный fix Cursor-артефактов из main chat без Task(t-800-factory), когда создаёшь или правишь agents/skills/commands/rules/hooks.
Factory в режиме PATCH — только файлы из fix-pack.
Шаги
0. Discovery + STATE
bash scripts/discover-target-project.sh --workspace "<WORKSPACE>" [--plugin-root "<PLUGIN_ROOT>"]
bash scripts/t800_loop_state.sh init --memory-path "<memory_path>"
# Read STATE.md
1. Read fix-pack
Путь: {memory_path}/fix-packs/<slug>.md
(шаблон: templates/fix-pack.md.template; из аудита: scripts/t800_audit_to_fixpack.py)
Batch из loop: если есть {memory_path}/loop-queue.md (после /t800-loop) — возьми пункты Open или сгенерируй packs (только status=open + LOW):
python3 scripts/t800_lessons_to_fixpack.py --memory-path "<memory_path>" --lessons "<run_id|path>"
Если pack нет — спроси slug / создай draft из аудита или queue, не угадывай files[].
2. Research (SKIP | LIGHT)
Default: SKIP или LIGHT, если в pack конкретные пути.
DEEP только если research_mode: deep / need_research: deep.
# SKIP → сразу brain
# LIGHT → Task(t-800-research-lead) с research_mode: light
bash scripts/t800_loop_state.sh touch --memory-path "<memory_path>" --stage "research" --message "skip|light|deep"
3. Brain
Task(t-800-brain-lead)
Обычно 1 domain. В brief_for_factory укажи: mode: PATCH, путь fix-pack, files[].
4. Factory PATCH
Task(t-800-factory)
Передай: mode: PATCH, fix-pack path, список файлов, success_criteria.
Factory не пишет вне files[].
5. Run gate
python3 scripts/t800_run_gate.py --memory-path "<memory_path>" \
[--require-validate] [--plugin-root "<PLUGIN_ROOT>"] \
[--require-plugin-audit-out "<DIR>"]
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 First seen · 120 lines · 0 tokens per session scan A 8e234377db24
t800-fix is a command published in the GitHub repository Khar-AG/t-800-agent (8 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,075 tokens. 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
quality-gate
Run formatter, linter, and type checks for a file or directory. Report remediation steps.
pn-audit-data
Design or review database schema — normalization, indexing strategy, migration plan, and data model decisions. Surgical command for database design. Use standalone or as part of pn-backend-audit.
pn-audit-performance
Identify and fix backend performance issues — N+1 queries, missing cache layers, blocking I/O, slow queries, and connection pool exhaustion. Surgical backend performance pass.
pn-delight
Add purposeful moments of joy, motion, and personality. Use when the design is correct and complete but feels flat and lifeless.
create-repro
Isolate a bug report into a minimal, standalone reproduction script or test case.
cleanup
Run a systematic cleanup on the provided code to resolve smells, simplify complexity, and enforce best practices.