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/mussolene/1c_hbk_bslWrote 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/mussolene/1c_hbk_bsl/task-fixer)<a href="https://agentmods.dev/agents/mussolene/1c_hbk_bsl/task-fixer"><img src="https://agentmods.dev/badge/agents/mussolene/1c_hbk_bsl/task-fixer.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 | $0.00019 | $0.00175 |
| Opus 5 | $0.00010 | $0.00088 |
| Sonnet 5 | $0.00004 | $0.00035 |
| Haiku 4.5 | $0.00002 | $0.00017 |
Grade A, and why
task-fixer 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.
What it actually says
You are the task-fixer.
Use AGENTS.md and docs/oacs-development.md. OACS/ACS is the durable workflow
surface; do not create or update repo-task-proof-loop files.
Use floating context: take only the compact OACS capsule plus verifier evidence,
then reconfirm against current files before editing.
Behavior:
- Reconfirm each reported problem in the current codebase before editing.
- Make the smallest safe change set.
- Avoid regressing already-passing checks.
- Rerun only the relevant checks.
- Record fix verification as ACS evidence when ACS is available.
- Do not write final sign-off; leave final verification to a fresh verifier.
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 · 21 lines · 19 tokens per session scan A e16f04c1047b
task-fixer is an agent published in the GitHub repository mussolene/1c_hbk_bsl (9 stars, last pushed 11d ago), licensed MIT. It adds 19 tokens to every session and 175 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 agents, from other repositories
bsl-verifier
An automated verifier for BSL, the programming language used by the 1C business-software platform. It checks method signatures, shared modules, metadata objects, static-analysis diagnostics, naming rules, and allowed characters.
1c-code-explorer
An analysis agent for existing 1C codebases. 1C is a business-software platform, and the agent traces how a change moves from user actions through program layers to stored data.
bsl-scout
A code explorer for 1C:Enterprise that gathers facts about how code and metadata are connected.
xml-runner
An automated checker for XML exports from 1C, a business-software platform. It compares the files on disk with their expected contents and checks metadata structure.
1c-code-explorer
A code-analysis assistant for 1C, a business software platform widely used for accounting and enterprise management.
1c-code-reviewer
A Russian-language code-review agent focused on the 1C business software platform.