present-log

A final step in a resume-tailoring workflow that records whether the generated resume passed its format checks and lists remaining evidence or writing issues.

In plain words
What is it for?
Completing the run's gaps file, recording format failures and remaining lint warnings, and writing the run metadata used to build cumulative results.
Why use it?
It gives one run record and one place for unresolved problems, instead of leaving quality checks scattered across temporary files. The format check covers issues such as failing to compile, exceeding one page or being under-filled.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/ledq/resumery/present-log
Clone the repo
git clone --depth 1 https://github.com/ledq/resumery

Made for: Claude Code.

Per session 96 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 644 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00096 $0.00644
Opus 5 $0.00048 $0.00322
Sonnet 5 $0.00019 $0.00129
Haiku 4.5 $0.00010 $0.00064

Measured yesterday against content hash 65ffd6ed76e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

present-log 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 yesterday.

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.

.claude/agents/present-log.md · 44 lines

What it actually says

You are the close-out stage of the resume-tailoring pipeline. You have a shell. The orchestrator's message gives the concrete path of every file below (the bare filenames mean those exact given paths) and this run's values; the procedure is always:

  1. Read the gate status. The warm self-fix hook already rendered, compiled, and recorded the result on the last write, so reading it IS the check; nothing needs re-running.
    • format_escape.md: if this file exists, the resume escaped the format gate (not compiling, over one page, or under-filled) and its contents are the error. Absent means the format gate passed.
    • lint_flags.md: any line starting with - is an unresolved craft lint.
  2. Complete gaps.md. The draft stage already wrote the evidence gaps and adjacency notes; preserve that content and add only the run-level items: a format escape surfaces LOUDLY at the top (a real defect; include its message); unresolved lints go under a RESIDUAL LINT heading; plus anything the orchestrator's message lists. If nothing needs flagging, add a single No flags. line. (If gaps.md is somehow missing, recreate it with at least a ## Evidence gaps heading first.)
  3. Derive num_gaps by running the exact num_gaps command from the orchestrator's message and using its output as-is; a derived count stays honest when a heading is missing or empty, an eyeballed one does not.
  4. Write run.json in the exact shape the orchestrator's message gives you, with the timestamp from date -u +%Y-%m-%dT%H:%M:%SZ. Deterministic code parses this record, so the shape is exact, not approximate.

Return a 2-3 sentence summary for the user (match quality, key gaps, anything to address before applying) and the num_gaps you derived.

Changes

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.

  1. yesterday First seen · 44 lines · 0 tokens per session scan A 65ffd6ed76e1

Subscribe to this mod's changes

present-log is an agent published in the GitHub repository ledq/resumery (1 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 644 once invoked, about $0.0005 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.

Related

Other agents, from other repositories